|
|
--- |
|
|
tags: |
|
|
- sentence-transformers |
|
|
- sentence-similarity |
|
|
- feature-extraction |
|
|
- generated_from_trainer |
|
|
- dataset_size:412178 |
|
|
- loss:MultipleNegativesRankingLoss |
|
|
base_model: answerdotai/ModernBERT-base |
|
|
widget: |
|
|
- source_sentence: "Clip off all parts from all bounding boxes that are outside of\ |
|
|
\ the image.\n\n Returns\n -------\n imgaug.BoundingBoxesOnImage\n\ |
|
|
\ Bounding boxes, clipped to fall within the image dimensions." |
|
|
sentences: |
|
|
- "def model_best(y1, y2, samples=1000, progressbar=True):\n \"\"\"\n Bayesian\ |
|
|
\ Estimation Supersedes the T-Test\n\n This model runs a Bayesian hypothesis\ |
|
|
\ comparing if y1 and y2 come\n from the same distribution. Returns are assumed\ |
|
|
\ to be T-distributed.\n\n In addition, computes annual volatility and Sharpe\ |
|
|
\ of in and\n out-of-sample periods.\n\n This model replicates the example\ |
|
|
\ used in:\n Kruschke, John. (2012) Bayesian estimation supersedes the t\n\ |
|
|
\ test. Journal of Experimental Psychology: General.\n\n Parameters\n \ |
|
|
\ ----------\n y1 : array-like\n Array of returns (e.g. in-sample)\n\ |
|
|
\ y2 : array-like\n Array of returns (e.g. out-of-sample)\n samples\ |
|
|
\ : int, optional\n Number of posterior samples to draw.\n\n Returns\n\ |
|
|
\ -------\n model : pymc.Model object\n PyMC3 model containing all\ |
|
|
\ random variables.\n trace : pymc3.sampling.BaseTrace object\n A PyMC3\ |
|
|
\ trace object that contains samples for each parameter\n of the posterior.\n\ |
|
|
\n See Also\n --------\n plot_stoch_vol : plotting of tochastic volatility\ |
|
|
\ model\n \"\"\"\n\n y = np.concatenate((y1, y2))\n\n mu_m = np.mean(y)\n\ |
|
|
\ mu_p = 0.000001 * 1 / np.std(y)**2\n\n sigma_low = np.std(y) / 1000\n\ |
|
|
\ sigma_high = np.std(y) * 1000\n with pm.Model() as model:\n group1_mean\ |
|
|
\ = pm.Normal('group1_mean', mu=mu_m, tau=mu_p,\n \ |
|
|
\ testval=y1.mean())\n group2_mean = pm.Normal('group2_mean', mu=mu_m,\ |
|
|
\ tau=mu_p,\n testval=y2.mean())\n group1_std\ |
|
|
\ = pm.Uniform('group1_std', lower=sigma_low,\n \ |
|
|
\ upper=sigma_high, testval=y1.std())\n group2_std = pm.Uniform('group2_std',\ |
|
|
\ lower=sigma_low,\n upper=sigma_high, testval=y2.std())\n\ |
|
|
\ nu = pm.Exponential('nu_minus_two', 1 / 29., testval=4.) + 2.\n\n \ |
|
|
\ returns_group1 = pm.StudentT('group1', nu=nu, mu=group1_mean,\n \ |
|
|
\ lam=group1_std**-2, observed=y1)\n returns_group2\ |
|
|
\ = pm.StudentT('group2', nu=nu, mu=group2_mean,\n \ |
|
|
\ lam=group2_std**-2, observed=y2)\n\n diff_of_means = pm.Deterministic('difference\ |
|
|
\ of means',\n group2_mean - group1_mean)\n\ |
|
|
\ pm.Deterministic('difference of stds',\n group2_std\ |
|
|
\ - group1_std)\n pm.Deterministic('effect size', diff_of_means /\n \ |
|
|
\ pm.math.sqrt((group1_std**2 +\n \ |
|
|
\ group2_std**2) / 2))\n\n pm.Deterministic('group1_annual_volatility',\n\ |
|
|
\ returns_group1.distribution.variance**.5 *\n \ |
|
|
\ np.sqrt(252))\n pm.Deterministic('group2_annual_volatility',\n\ |
|
|
\ returns_group2.distribution.variance**.5 *\n \ |
|
|
\ np.sqrt(252))\n\n pm.Deterministic('group1_sharpe',\ |
|
|
\ returns_group1.distribution.mean /\n returns_group1.distribution.variance**.5\ |
|
|
\ *\n np.sqrt(252))\n pm.Deterministic('group2_sharpe',\ |
|
|
\ returns_group2.distribution.mean /\n returns_group2.distribution.variance**.5\ |
|
|
\ *\n np.sqrt(252))\n\n trace = pm.sample(samples,\ |
|
|
\ progressbar=progressbar)\n return model, trace" |
|
|
- "def clip_out_of_image(self):\n \"\"\"\n Clip off all parts from\ |
|
|
\ all bounding boxes that are outside of the image.\n\n Returns\n \ |
|
|
\ -------\n imgaug.BoundingBoxesOnImage\n Bounding boxes,\ |
|
|
\ clipped to fall within the image dimensions.\n\n \"\"\"\n bbs_cut\ |
|
|
\ = [bb.clip_out_of_image(self.shape)\n for bb in self.bounding_boxes\ |
|
|
\ if bb.is_partly_within_image(self.shape)]\n return BoundingBoxesOnImage(bbs_cut,\ |
|
|
\ shape=self.shape)" |
|
|
- "def _initPermanence(self, potential, connectedPct):\n \"\"\"\n Initializes\ |
|
|
\ the permanences of a column. The method\n returns a 1-D array the size of\ |
|
|
\ the input, where each entry in the\n array represents the initial permanence\ |
|
|
\ value between the input bit\n at the particular index in the array, and the\ |
|
|
\ column represented by\n the 'index' parameter.\n\n Parameters:\n ----------------------------\n\ |
|
|
\ :param potential: A numpy array specifying the potential pool of the column.\n\ |
|
|
\ Permanence values will only be generated for input bits\n\ |
|
|
\ corresponding to indices for which the mask value is 1.\n\ |
|
|
\ :param connectedPct: A value between 0 or 1 governing the chance, for each\n\ |
|
|
\ permanence, that the initial permanence value will\n\ |
|
|
\ be a value that is considered connected.\n \"\"\"\ |
|
|
\n # Determine which inputs bits will start out as connected\n # to the\ |
|
|
\ inputs. Initially a subset of the input bits in a\n # column's potential\ |
|
|
\ pool will be connected. This number is\n # given by the parameter \"connectedPct\"\ |
|
|
\n perm = numpy.zeros(self._numInputs, dtype=realDType)\n for i in xrange(self._numInputs):\n\ |
|
|
\ if (potential[i] < 1):\n continue\n\n if (self._random.getReal64()\ |
|
|
\ <= connectedPct):\n perm[i] = self._initPermConnected()\n else:\n\ |
|
|
\ perm[i] = self._initPermNonConnected()\n\n # Clip off low values.\ |
|
|
\ Since we use a sparse representation\n # to store the permanence values this\ |
|
|
\ helps reduce memory\n # requirements.\n perm[perm < self._synPermTrimThreshold]\ |
|
|
\ = 0\n\n return perm" |
|
|
- source_sentence: "Perform a weighted average over dicts that are each on a different\ |
|
|
\ node\n Input: local_name2valcount: dict mapping key -> (value, count)\n \ |
|
|
\ Returns: key -> mean" |
|
|
sentences: |
|
|
- "def MotionBlur(k=5, angle=(0, 360), direction=(-1.0, 1.0), order=1, name=None,\ |
|
|
\ deterministic=False, random_state=None):\n \"\"\"\n Augmenter that sharpens\ |
|
|
\ images and overlays the result with the original image.\n\n dtype support::\n\ |
|
|
\n See ``imgaug.augmenters.convolutional.Convolve``.\n\n Parameters\n\ |
|
|
\ ----------\n k : int or tuple of int or list of int or imgaug.parameters.StochasticParameter,\ |
|
|
\ optional\n Kernel size to use.\n\n * If a single int, then\ |
|
|
\ that value will be used for the height\n and width of the kernel.\n\ |
|
|
\ * If a tuple of two ints ``(a, b)``, then the kernel size will be\n\ |
|
|
\ sampled from the interval ``[a..b]``.\n * If a list,\ |
|
|
\ then a random value will be sampled from that list per image.\n *\ |
|
|
\ If a StochasticParameter, then ``N`` samples will be drawn from\n \ |
|
|
\ that parameter per ``N`` input images, each representing the kernel\n \ |
|
|
\ size for the nth image.\n\n angle : number or tuple of number or\ |
|
|
\ list of number or imgaug.parameters.StochasticParameter, optional\n Angle\ |
|
|
\ of the motion blur in degrees (clockwise, relative to top center direction).\n\ |
|
|
\n * If a number, exactly that value will be used.\n * If\ |
|
|
\ a tuple ``(a, b)``, a random value from the range ``a <= x <= b`` will\n \ |
|
|
\ be sampled per image.\n * If a list, then a random value\ |
|
|
\ will be sampled from that list per image.\n * If a StochasticParameter,\ |
|
|
\ a value will be sampled from the\n parameter per image.\n\n \ |
|
|
\ direction : number or tuple of number or list of number or imgaug.parameters.StochasticParameter,\ |
|
|
\ optional\n Forward/backward direction of the motion blur. Lower values\ |
|
|
\ towards -1.0 will point the motion blur towards\n the back (with angle\ |
|
|
\ provided via `angle`). Higher values towards 1.0 will point the motion blur\ |
|
|
\ forward.\n A value of 0.0 leads to a uniformly (but still angled) motion\ |
|
|
\ blur.\n\n * If a number, exactly that value will be used.\n \ |
|
|
\ * If a tuple ``(a, b)``, a random value from the range ``a <= x <= b``\ |
|
|
\ will\n be sampled per image.\n * If a list, then a random\ |
|
|
\ value will be sampled from that list per image.\n * If a StochasticParameter,\ |
|
|
\ a value will be sampled from the\n parameter per image.\n\n \ |
|
|
\ order : int or iterable of int or imgaug.ALL or imgaug.parameters.StochasticParameter,\ |
|
|
\ optional\n Interpolation order to use when rotating the kernel according\ |
|
|
\ to `angle`.\n See :func:`imgaug.augmenters.geometric.Affine.__init__`.\n\ |
|
|
\ Recommended to be ``0`` or ``1``, with ``0`` being faster, but less continuous/smooth\ |
|
|
\ as `angle` is changed,\n particularly around multiple of 45 degrees.\n\ |
|
|
\n name : None or str, optional\n See :func:`imgaug.augmenters.meta.Augmenter.__init__`.\n\ |
|
|
\n deterministic : bool, optional\n See :func:`imgaug.augmenters.meta.Augmenter.__init__`.\n\ |
|
|
\n random_state : None or int or numpy.random.RandomState, optional\n \ |
|
|
\ See :func:`imgaug.augmenters.meta.Augmenter.__init__`.\n\n Examples\n \ |
|
|
\ --------\n >>> aug = iaa.MotionBlur(k=15)\n\n Create a motion blur augmenter\ |
|
|
\ with kernel size of 15x15.\n\n >>> aug = iaa.MotionBlur(k=15, angle=[-45,\ |
|
|
\ 45])\n\n Create a motion blur augmenter with kernel size of 15x15 and a blur\ |
|
|
\ angle of either -45 or 45 degrees (randomly\n picked per image).\n\n \"\ |
|
|
\"\"\n # TODO allow (1, None) and set to identity matrix if k == 1\n k_param\ |
|
|
\ = iap.handle_discrete_param(k, \"k\", value_range=(3, None), tuple_to_uniform=True,\ |
|
|
\ list_to_choice=True,\n allow_floats=False)\n\ |
|
|
\ angle_param = iap.handle_continuous_param(angle, \"angle\", value_range=None,\ |
|
|
\ tuple_to_uniform=True,\n list_to_choice=True)\n\ |
|
|
\ direction_param = iap.handle_continuous_param(direction, \"direction\", value_range=(-1.0-1e-6,\ |
|
|
\ 1.0+1e-6),\n tuple_to_uniform=True,\ |
|
|
\ list_to_choice=True)\n\n def create_matrices(image, nb_channels, random_state_func):\n\ |
|
|
\ # avoid cyclic import between blur and geometric\n from . import\ |
|
|
\ geometric as iaa_geometric\n\n # force discrete for k_sample via int()\ |
|
|
\ in case of stochastic parameter\n k_sample = int(k_param.draw_sample(random_state=random_state_func))\n\ |
|
|
\ angle_sample = angle_param.draw_sample(random_state=random_state_func)\n\ |
|
|
\ direction_sample = direction_param.draw_sample(random_state=random_state_func)\n\ |
|
|
\n k_sample = k_sample if k_sample % 2 != 0 else k_sample + 1\n \ |
|
|
\ direction_sample = np.clip(direction_sample, -1.0, 1.0)\n direction_sample\ |
|
|
\ = (direction_sample + 1.0) / 2.0\n\n matrix = np.zeros((k_sample, k_sample),\ |
|
|
\ dtype=np.float32)\n matrix[:, k_sample//2] = np.linspace(float(direction_sample),\ |
|
|
\ 1.0 - float(direction_sample), num=k_sample)\n rot = iaa_geometric.Affine(rotate=angle_sample,\ |
|
|
\ order=order)\n matrix = (rot.augment_image((matrix * 255).astype(np.uint8))\ |
|
|
\ / 255.0).astype(np.float32)\n\n return [matrix/np.sum(matrix)] * nb_channels\n\ |
|
|
\n if name is None:\n name = \"Unnamed%s\" % (ia.caller_name(),)\n\n\ |
|
|
\ return iaa_convolutional.Convolve(create_matrices, name=name, deterministic=deterministic,\n\ |
|
|
\ random_state=random_state)" |
|
|
- "def rolling_sharpe(returns, rolling_sharpe_window):\n \"\"\"\n Determines\ |
|
|
\ the rolling Sharpe ratio of a strategy.\n\n Parameters\n ----------\n\ |
|
|
\ returns : pd.Series\n Daily returns of the strategy, noncumulative.\n\ |
|
|
\ - See full explanation in tears.create_full_tear_sheet.\n rolling_sharpe_window\ |
|
|
\ : int\n Length of rolling window, in days, over which to compute.\n\n\ |
|
|
\ Returns\n -------\n pd.Series\n Rolling Sharpe ratio.\n\n \ |
|
|
\ Note\n -----\n See https://en.wikipedia.org/wiki/Sharpe_ratio for more\ |
|
|
\ details.\n \"\"\"\n\n return returns.rolling(rolling_sharpe_window).mean()\ |
|
|
\ \\\n / returns.rolling(rolling_sharpe_window).std() \\\n * np.sqrt(APPROX_BDAYS_PER_YEAR)" |
|
|
- "def mpi_weighted_mean(comm, local_name2valcount):\n \"\"\"\n Perform a\ |
|
|
\ weighted average over dicts that are each on a different node\n Input: local_name2valcount:\ |
|
|
\ dict mapping key -> (value, count)\n Returns: key -> mean\n \"\"\"\n \ |
|
|
\ all_name2valcount = comm.gather(local_name2valcount)\n if comm.rank ==\ |
|
|
\ 0:\n name2sum = defaultdict(float)\n name2count = defaultdict(float)\n\ |
|
|
\ for n2vc in all_name2valcount:\n for (name, (val, count))\ |
|
|
\ in n2vc.items():\n try:\n val = float(val)\n\ |
|
|
\ except ValueError:\n if comm.rank == 0:\n\ |
|
|
\ warnings.warn('WARNING: tried to compute mean on non-float\ |
|
|
\ {}={}'.format(name, val))\n else:\n name2sum[name]\ |
|
|
\ += val * count\n name2count[name] += count\n return\ |
|
|
\ {name : name2sum[name] / name2count[name] for name in name2sum}\n else:\n\ |
|
|
\ return {}" |
|
|
- source_sentence: "Generate and return the following encoder related substitution\ |
|
|
\ variables:\n\n encoderSpecsStr:\n For the base description file, this string\ |
|
|
\ defines the default\n encoding dicts for each encoder. For example:\n \ |
|
|
\ '__gym_encoder' : { 'fieldname': 'gym',\n 'n': 13,\n \ |
|
|
\ 'name': 'gym',\n 'type': 'SDRCategoryEncoder',\n 'w': 7},\n\ |
|
|
\ '__address_encoder' : { 'fieldname': 'address',\n 'n': 13,\n\ |
|
|
\ 'name': 'address',\n 'type': 'SDRCategoryEncoder',\n \ |
|
|
\ 'w': 7}\n\n encoderSchemaStr:\n For the base description file, this\ |
|
|
\ is a list containing a\n DeferredDictLookup entry for each encoder. For example:\n\ |
|
|
\ [DeferredDictLookup('__gym_encoder'),\n DeferredDictLookup('__address_encoder'),\n\ |
|
|
\ DeferredDictLookup('__timestamp_timeOfDay_encoder'),\n DeferredDictLookup('__timestamp_dayOfWeek_encoder'),\n\ |
|
|
\ DeferredDictLookup('__consumption_encoder')],\n\n permEncoderChoicesStr:\n\ |
|
|
\ For the permutations file, this defines the possible\n encoder dicts for\ |
|
|
\ each encoder. For example:\n '__timestamp_dayOfWeek_encoder': [\n \ |
|
|
\ None,\n {'fieldname':'timestamp',\n \ |
|
|
\ 'name': 'timestamp_timeOfDay',\n 'type':'DateEncoder'\n\ |
|
|
\ 'dayOfWeek': (7,1)\n },\n \ |
|
|
\ {'fieldname':'timestamp',\n 'name': 'timestamp_timeOfDay',\n\ |
|
|
\ 'type':'DateEncoder'\n 'dayOfWeek':\ |
|
|
\ (7,3)\n },\n ],\n\n '__field_consumption_encoder':\ |
|
|
\ [\n None,\n {'fieldname':'consumption',\n\ |
|
|
\ 'name': 'consumption',\n 'type':'AdaptiveScalarEncoder',\n\ |
|
|
\ 'n': 13,\n 'w': 7,\n \ |
|
|
\ }\n ]\n\n\n\n Parameters:\n --------------------------------------------------\n\ |
|
|
\ includedFields: item from the 'includedFields' section of the\n \ |
|
|
\ description JSON object. This is a list of dicts, each\n \ |
|
|
\ dict defining the field name, type, and optional min\n \ |
|
|
\ and max values.\n\n retval: (encoderSpecsStr, encoderSchemaStr permEncoderChoicesStr)" |
|
|
sentences: |
|
|
- "def _generateEncoderStringsV1(includedFields):\n \"\"\" Generate and return\ |
|
|
\ the following encoder related substitution variables:\n\n encoderSpecsStr:\n\ |
|
|
\ For the base description file, this string defines the default\n encoding\ |
|
|
\ dicts for each encoder. For example:\n '__gym_encoder' : { 'fieldname':\ |
|
|
\ 'gym',\n 'n': 13,\n 'name': 'gym',\n 'type': 'SDRCategoryEncoder',\n\ |
|
|
\ 'w': 7},\n '__address_encoder' : { 'fieldname': 'address',\n\ |
|
|
\ 'n': 13,\n 'name': 'address',\n 'type': 'SDRCategoryEncoder',\n\ |
|
|
\ 'w': 7}\n\n encoderSchemaStr:\n For the base description file,\ |
|
|
\ this is a list containing a\n DeferredDictLookup entry for each encoder.\ |
|
|
\ For example:\n [DeferredDictLookup('__gym_encoder'),\n DeferredDictLookup('__address_encoder'),\n\ |
|
|
\ DeferredDictLookup('__timestamp_timeOfDay_encoder'),\n DeferredDictLookup('__timestamp_dayOfWeek_encoder'),\n\ |
|
|
\ DeferredDictLookup('__consumption_encoder')],\n\n permEncoderChoicesStr:\n\ |
|
|
\ For the permutations file, this defines the possible\n encoder dicts for\ |
|
|
\ each encoder. For example:\n '__timestamp_dayOfWeek_encoder': [\n \ |
|
|
\ None,\n {'fieldname':'timestamp',\n \ |
|
|
\ 'name': 'timestamp_timeOfDay',\n 'type':'DateEncoder'\n\ |
|
|
\ 'dayOfWeek': (7,1)\n },\n \ |
|
|
\ {'fieldname':'timestamp',\n 'name': 'timestamp_timeOfDay',\n\ |
|
|
\ 'type':'DateEncoder'\n 'dayOfWeek':\ |
|
|
\ (7,3)\n },\n ],\n\n '__field_consumption_encoder':\ |
|
|
\ [\n None,\n {'fieldname':'consumption',\n\ |
|
|
\ 'name': 'consumption',\n 'type':'AdaptiveScalarEncoder',\n\ |
|
|
\ 'n': 13,\n 'w': 7,\n \ |
|
|
\ }\n ]\n\n\n\n Parameters:\n --------------------------------------------------\n\ |
|
|
\ includedFields: item from the 'includedFields' section of the\n \ |
|
|
\ description JSON object. This is a list of dicts, each\n \ |
|
|
\ dict defining the field name, type, and optional min\n \ |
|
|
\ and max values.\n\n retval: (encoderSpecsStr, encoderSchemaStr permEncoderChoicesStr)\n\ |
|
|
\n\n \"\"\"\n\n # ------------------------------------------------------------------------\n\ |
|
|
\ # First accumulate the possible choices for each encoder\n encoderChoicesList\ |
|
|
\ = []\n for fieldInfo in includedFields:\n\n fieldName = fieldInfo['fieldName']\n\ |
|
|
\n # Get the list of encoder choices for this field\n (choicesList, aggFunction)\ |
|
|
\ = _generateEncoderChoicesV1(fieldInfo)\n encoderChoicesList.extend(choicesList)\n\ |
|
|
\n\n # ------------------------------------------------------------------------\n\ |
|
|
\ # Generate the string containing the encoder specs and encoder schema. See\n\ |
|
|
\ # the function comments for an example of the encoderSpecsStr and\n # encoderSchemaStr\n\ |
|
|
\ #\n encoderSpecsList = []\n for encoderChoices in encoderChoicesList:\n \ |
|
|
\ # Use the last choice as the default in the base file because the 1st is\n\ |
|
|
\ # often None\n encoder = encoderChoices[-1]\n\n # Check for bad characters\n\ |
|
|
\ for c in _ILLEGAL_FIELDNAME_CHARACTERS:\n if encoder['name'].find(c)\ |
|
|
\ >= 0:\n raise _ExpGeneratorException(\"Illegal character in field: %r\ |
|
|
\ (%r)\" % (\n c, encoder['name']))\n\n encoderSpecsList.append(\"\ |
|
|
%s: \\n%s%s\" % (\n _quoteAndEscape(encoder['name']),\n 2*_ONE_INDENT,\n\ |
|
|
\ pprint.pformat(encoder, indent=2*_INDENT_STEP)))\n\n encoderSpecsStr\ |
|
|
\ = ',\\n '.join(encoderSpecsList)\n\n\n # ------------------------------------------------------------------------\n\ |
|
|
\ # Generate the string containing the permutation encoder choices. See the\n\ |
|
|
\ # function comments above for an example of the permEncoderChoicesStr\n\n\ |
|
|
\ permEncoderChoicesList = []\n for encoderChoices in encoderChoicesList:\n\ |
|
|
\ permEncoderChoicesList.append(\"%s: %s,\" % (\n _quoteAndEscape(encoderChoices[-1]['name']),\n\ |
|
|
\ pprint.pformat(encoderChoices, indent=2*_INDENT_STEP)))\n permEncoderChoicesStr\ |
|
|
\ = '\\n'.join(permEncoderChoicesList)\n permEncoderChoicesStr = _indentLines(permEncoderChoicesStr,\ |
|
|
\ 1,\n indentFirstLine=False)\n\n # Return\ |
|
|
\ results\n return (encoderSpecsStr, permEncoderChoicesStr)" |
|
|
- "def shift(self, top=None, right=None, bottom=None, left=None):\n \"\"\"\ |
|
|
\n Shift/move the line strings from one or more image sides.\n\n \ |
|
|
\ Parameters\n ----------\n top : None or int, optional\n \ |
|
|
\ Amount of pixels by which to shift all bounding boxes from the\n \ |
|
|
\ top.\n\n right : None or int, optional\n Amount of pixels\ |
|
|
\ by which to shift all bounding boxes from the\n right.\n\n \ |
|
|
\ bottom : None or int, optional\n Amount of pixels by which to shift\ |
|
|
\ all bounding boxes from the\n bottom.\n\n left : None or int,\ |
|
|
\ optional\n Amount of pixels by which to shift all bounding boxes\ |
|
|
\ from the\n left.\n\n Returns\n -------\n imgaug.augmentables.lines.LineStringsOnImage\n\ |
|
|
\ Shifted line strings.\n\n \"\"\"\n lss_new = [ls.shift(top=top,\ |
|
|
\ right=right, bottom=bottom, left=left)\n for ls in self.line_strings]\n\ |
|
|
\ return LineStringsOnImage(lss_new, shape=self.shape)" |
|
|
- "def cross_entropy_reward_loss(logits, actions, rewards, name=None):\n \"\"\ |
|
|
\"Calculate the loss for Policy Gradient Network.\n\n Parameters\n ----------\n\ |
|
|
\ logits : tensor\n The network outputs without softmax. This function\ |
|
|
\ implements softmax inside.\n actions : tensor or placeholder\n The\ |
|
|
\ agent actions.\n rewards : tensor or placeholder\n The rewards.\n\n\ |
|
|
\ Returns\n --------\n Tensor\n The TensorFlow loss function.\n\ |
|
|
\n Examples\n ----------\n >>> states_batch_pl = tf.placeholder(tf.float32,\ |
|
|
\ shape=[None, D])\n >>> network = InputLayer(states_batch_pl, name='input')\n\ |
|
|
\ >>> network = DenseLayer(network, n_units=H, act=tf.nn.relu, name='relu1')\n\ |
|
|
\ >>> network = DenseLayer(network, n_units=3, name='out')\n >>> probs =\ |
|
|
\ network.outputs\n >>> sampling_prob = tf.nn.softmax(probs)\n >>> actions_batch_pl\ |
|
|
\ = tf.placeholder(tf.int32, shape=[None])\n >>> discount_rewards_batch_pl\ |
|
|
\ = tf.placeholder(tf.float32, shape=[None])\n >>> loss = tl.rein.cross_entropy_reward_loss(probs,\ |
|
|
\ actions_batch_pl, discount_rewards_batch_pl)\n >>> train_op = tf.train.RMSPropOptimizer(learning_rate,\ |
|
|
\ decay_rate).minimize(loss)\n\n \"\"\"\n cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=actions,\ |
|
|
\ logits=logits, name=name)\n\n return tf.reduce_sum(tf.multiply(cross_entropy,\ |
|
|
\ rewards))" |
|
|
- source_sentence: "Translate an index into coordinates, using the given coordinate\ |
|
|
\ system.\n\n Similar to ``numpy.unravel_index``.\n\n :param index: (int) The\ |
|
|
\ index of the point. The coordinates are expressed as a \n single index\ |
|
|
\ by using the dimensions as a mixed radix definition. For \n example,\ |
|
|
\ in dimensions 42x10, the point [1, 4] is index \n 1*420 + 4*10 = 460.\n\ |
|
|
\n :param dimensions (list of ints) The coordinate system.\n\n :returns: (list)\ |
|
|
\ of coordinates of length ``len(dimensions)``." |
|
|
sentences: |
|
|
- "def coordinatesFromIndex(index, dimensions):\n \"\"\"\n Translate an index\ |
|
|
\ into coordinates, using the given coordinate system.\n\n Similar to ``numpy.unravel_index``.\n\ |
|
|
\n :param index: (int) The index of the point. The coordinates are expressed\ |
|
|
\ as a \n single index by using the dimensions as a mixed radix definition.\ |
|
|
\ For \n example, in dimensions 42x10, the point [1, 4] is index \n \ |
|
|
\ 1*420 + 4*10 = 460.\n\n :param dimensions (list of ints) The coordinate\ |
|
|
\ system.\n\n :returns: (list) of coordinates of length ``len(dimensions)``.\n\ |
|
|
\ \"\"\"\n coordinates = [0] * len(dimensions)\n\n shifted = index\n for i\ |
|
|
\ in xrange(len(dimensions) - 1, 0, -1):\n coordinates[i] = shifted % dimensions[i]\n\ |
|
|
\ shifted = shifted / dimensions[i]\n\n coordinates[0] = shifted\n\n return\ |
|
|
\ coordinates" |
|
|
- "def step(self, observation, **extra_feed):\n \"\"\"\n Compute next\ |
|
|
\ action(s) given the observation(s)\n\n Parameters:\n ----------\n\ |
|
|
\n observation observation data (either single or a batch)\n\n \ |
|
|
\ **extra_feed additional data such as state or mask (names of the arguments\ |
|
|
\ should match the ones in constructor, see __init__)\n\n Returns:\n \ |
|
|
\ -------\n (action, value estimate, next state, negative log likelihood\ |
|
|
\ of the action under current policy parameters) tuple\n \"\"\"\n\n \ |
|
|
\ a, v, state, neglogp = self._evaluate([self.action, self.vf, self.state,\ |
|
|
\ self.neglogp], observation, **extra_feed)\n if state.size == 0:\n \ |
|
|
\ state = None\n return a, v, state, neglogp" |
|
|
- "def pretty_eta(seconds_left):\n \"\"\"Print the number of seconds in human\ |
|
|
\ readable format.\n\n Examples:\n 2 days\n 2 hours and 37 minutes\n\ |
|
|
\ less than a minute\n\n Paramters\n ---------\n seconds_left: int\n\ |
|
|
\ Number of seconds to be converted to the ETA\n Returns\n -------\n\ |
|
|
\ eta: str\n String representing the pretty ETA.\n \"\"\"\n minutes_left\ |
|
|
\ = seconds_left // 60\n seconds_left %= 60\n hours_left = minutes_left\ |
|
|
\ // 60\n minutes_left %= 60\n days_left = hours_left // 24\n hours_left\ |
|
|
\ %= 24\n\n def helper(cnt, name):\n return \"{} {}{}\".format(str(cnt),\ |
|
|
\ name, ('s' if cnt > 1 else ''))\n\n if days_left > 0:\n msg = helper(days_left,\ |
|
|
\ 'day')\n if hours_left > 0:\n msg += ' and ' + helper(hours_left,\ |
|
|
\ 'hour')\n return msg\n if hours_left > 0:\n msg = helper(hours_left,\ |
|
|
\ 'hour')\n if minutes_left > 0:\n msg += ' and ' + helper(minutes_left,\ |
|
|
\ 'minute')\n return msg\n if minutes_left > 0:\n return helper(minutes_left,\ |
|
|
\ 'minute')\n return 'less than a minute'" |
|
|
- source_sentence: Validates control dictionary for the experiment context |
|
|
sentences: |
|
|
- "def load_file_list(path=None, regx='\\.jpg', printable=True, keep_prefix=False):\n\ |
|
|
\ r\"\"\"Return a file list in a folder by given a path and regular expression.\n\ |
|
|
\n Parameters\n ----------\n path : str or None\n A folder path,\ |
|
|
\ if `None`, use the current directory.\n regx : str\n The regx of file\ |
|
|
\ name.\n printable : boolean\n Whether to print the files infomation.\n\ |
|
|
\ keep_prefix : boolean\n Whether to keep path in the file name.\n\n\ |
|
|
\ Examples\n ----------\n >>> file_list = tl.files.load_file_list(path=None,\ |
|
|
\ regx='w1pre_[0-9]+\\.(npz)')\n\n \"\"\"\n if path is None:\n path\ |
|
|
\ = os.getcwd()\n file_list = os.listdir(path)\n return_list = []\n for\ |
|
|
\ _, f in enumerate(file_list):\n if re.search(regx, f):\n return_list.append(f)\n\ |
|
|
\ # return_list.sort()\n if keep_prefix:\n for i, f in enumerate(return_list):\n\ |
|
|
\ return_list[i] = os.path.join(path, f)\n\n if printable:\n \ |
|
|
\ logging.info('Match file list = %s' % return_list)\n logging.info('Number\ |
|
|
\ of files = %d' % len(return_list))\n return return_list" |
|
|
- "def getCompletingSwarms(self):\n \"\"\"Return the list of all completing swarms.\n\ |
|
|
\n Parameters:\n ---------------------------------------------------------------------\n\ |
|
|
\ retval: list of active swarm Ids\n \"\"\"\n swarmIds = []\n for\ |
|
|
\ swarmId, info in self._state['swarms'].iteritems():\n if info['status']\ |
|
|
\ == 'completing':\n swarmIds.append(swarmId)\n\n return swarmIds" |
|
|
- "def __validateExperimentControl(self, control):\n \"\"\" Validates control\ |
|
|
\ dictionary for the experiment context\"\"\"\n # Validate task list\n taskList\ |
|
|
\ = control.get('tasks', None)\n if taskList is not None:\n taskLabelsList\ |
|
|
\ = []\n\n for task in taskList:\n validateOpfJsonValue(task, \"opfTaskSchema.json\"\ |
|
|
)\n validateOpfJsonValue(task['taskControl'], \"opfTaskControlSchema.json\"\ |
|
|
)\n\n taskLabel = task['taskLabel']\n\n assert isinstance(taskLabel,\ |
|
|
\ types.StringTypes), \\\n \"taskLabel type: %r\" % type(taskLabel)\n\ |
|
|
\ assert len(taskLabel) > 0, \"empty string taskLabel not is allowed\"\n\ |
|
|
\n taskLabelsList.append(taskLabel.lower())\n\n taskLabelDuplicates\ |
|
|
\ = filter(lambda x: taskLabelsList.count(x) > 1,\n \ |
|
|
\ taskLabelsList)\n assert len(taskLabelDuplicates) == 0, \\\n \ |
|
|
\ \"Duplcate task labels are not allowed: %s\" % taskLabelDuplicates\n\ |
|
|
\n return" |
|
|
pipeline_tag: sentence-similarity |
|
|
library_name: sentence-transformers |
|
|
--- |
|
|
|
|
|
# SentenceTransformer based on answerdotai/ModernBERT-base |
|
|
|
|
|
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the code_search_net dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. |
|
|
|
|
|
## Model Details |
|
|
|
|
|
### Model Description |
|
|
- **Model Type:** Sentence Transformer |
|
|
- **Base model:** [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) <!-- at revision 8949b909ec900327062f0ebf497f51aef5e6f0c8 --> |
|
|
- **Maximum Sequence Length:** 4096 tokens |
|
|
- **Output Dimensionality:** 768 dimensions |
|
|
- **Similarity Function:** Cosine Similarity |
|
|
- **Training Dataset:** |
|
|
- code_search_net |
|
|
<!-- - **Language:** Unknown --> |
|
|
<!-- - **License:** Unknown --> |
|
|
|
|
|
### Model Sources |
|
|
|
|
|
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net) |
|
|
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) |
|
|
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) |
|
|
|
|
|
### Full Model Architecture |
|
|
|
|
|
``` |
|
|
SentenceTransformer( |
|
|
(0): Transformer({'max_seq_length': 4096, 'do_lower_case': False}) with Transformer model: ModernBertModel |
|
|
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) |
|
|
) |
|
|
``` |
|
|
|
|
|
## Usage |
|
|
|
|
|
### Direct Usage (Sentence Transformers) |
|
|
|
|
|
First install the Sentence Transformers library: |
|
|
|
|
|
```bash |
|
|
pip install -U sentence-transformers |
|
|
``` |
|
|
|
|
|
Then you can load this model and run inference. |
|
|
```python |
|
|
from sentence_transformers import SentenceTransformer |
|
|
|
|
|
# Download from the 🤗 Hub |
|
|
model = SentenceTransformer("juanwisz/modernbert-python-code-retrieval") |
|
|
# Run inference |
|
|
sentences = [ |
|
|
'Validates control dictionary for the experiment context', |
|
|
'def __validateExperimentControl(self, control):\n """ Validates control dictionary for the experiment context"""\n # Validate task list\n taskList = control.get(\'tasks\', None)\n if taskList is not None:\n taskLabelsList = []\n\n for task in taskList:\n validateOpfJsonValue(task, "opfTaskSchema.json")\n validateOpfJsonValue(task[\'taskControl\'], "opfTaskControlSchema.json")\n\n taskLabel = task[\'taskLabel\']\n\n assert isinstance(taskLabel, types.StringTypes), \\\n "taskLabel type: %r" % type(taskLabel)\n assert len(taskLabel) > 0, "empty string taskLabel not is allowed"\n\n taskLabelsList.append(taskLabel.lower())\n\n taskLabelDuplicates = filter(lambda x: taskLabelsList.count(x) > 1,\n taskLabelsList)\n assert len(taskLabelDuplicates) == 0, \\\n "Duplcate task labels are not allowed: %s" % taskLabelDuplicates\n\n return', |
|
|
'def load_file_list(path=None, regx=\'\\.jpg\', printable=True, keep_prefix=False):\n r"""Return a file list in a folder by given a path and regular expression.\n\n Parameters\n ----------\n path : str or None\n A folder path, if `None`, use the current directory.\n regx : str\n The regx of file name.\n printable : boolean\n Whether to print the files infomation.\n keep_prefix : boolean\n Whether to keep path in the file name.\n\n Examples\n ----------\n >>> file_list = tl.files.load_file_list(path=None, regx=\'w1pre_[0-9]+\\.(npz)\')\n\n """\n if path is None:\n path = os.getcwd()\n file_list = os.listdir(path)\n return_list = []\n for _, f in enumerate(file_list):\n if re.search(regx, f):\n return_list.append(f)\n # return_list.sort()\n if keep_prefix:\n for i, f in enumerate(return_list):\n return_list[i] = os.path.join(path, f)\n\n if printable:\n logging.info(\'Match file list = %s\' % return_list)\n logging.info(\'Number of files = %d\' % len(return_list))\n return return_list', |
|
|
] |
|
|
embeddings = model.encode(sentences) |
|
|
print(embeddings.shape) |
|
|
# [3, 768] |
|
|
|
|
|
# Get the similarity scores for the embeddings |
|
|
similarities = model.similarity(embeddings, embeddings) |
|
|
print(similarities.shape) |
|
|
# [3, 3] |
|
|
``` |
|
|
|
|
|
<!-- |
|
|
### Direct Usage (Transformers) |
|
|
|
|
|
<details><summary>Click to see the direct usage in Transformers</summary> |
|
|
|
|
|
</details> |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
### Downstream Usage (Sentence Transformers) |
|
|
|
|
|
You can finetune this model on your own dataset. |
|
|
|
|
|
<details><summary>Click to expand</summary> |
|
|
|
|
|
</details> |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
### Out-of-Scope Use |
|
|
|
|
|
*List how the model may foreseeably be misused and address what users ought not to do with the model.* |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
## Bias, Risks and Limitations |
|
|
|
|
|
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
### Recommendations |
|
|
|
|
|
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* |
|
|
--> |
|
|
|
|
|
## Training Details |
|
|
|
|
|
### Training Dataset |
|
|
|
|
|
#### code_search_net |
|
|
|
|
|
* Dataset: code_search_net |
|
|
* Size: 412,178 training samples |
|
|
* Columns: <code>query</code> and <code>positive</code> |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | query | positive | |
|
|
|:--------|:------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------| |
|
|
| type | string | string | |
|
|
| details | <ul><li>min: 4 tokens</li><li>mean: 73.72 tokens</li><li>max: 2258 tokens</li></ul> | <ul><li>min: 46 tokens</li><li>mean: 300.87 tokens</li><li>max: 3119 tokens</li></ul> | |
|
|
* Samples: |
|
|
| query | positive | |
|
|
|:------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
|
|
| <code>Extracts the list of arguments that start with any of the specified prefix values</code> | <code>def findArgs(args, prefixes):<br> """<br> Extracts the list of arguments that start with any of the specified prefix values<br> """<br> return list([<br> arg for arg in args<br> if len([p for p in prefixes if arg.lower().startswith(p.lower())]) > 0<br> ])</code> | |
|
|
| <code>Removes any arguments in the supplied list that are contained in the specified blacklist</code> | <code>def stripArgs(args, blacklist):<br> """<br> Removes any arguments in the supplied list that are contained in the specified blacklist<br> """<br> blacklist = [b.lower() for b in blacklist]<br> return list([arg for arg in args if arg.lower() not in blacklist])</code> | |
|
|
| <code>Executes a child process and captures its output</code> | <code>def capture(command, input=None, cwd=None, shell=False, raiseOnError=False):<br> """<br> Executes a child process and captures its output<br> """<br> <br> # Attempt to execute the child process<br> proc = subprocess.Popen(command, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, cwd=cwd, shell=shell, universal_newlines=True)<br> (stdout, stderr) = proc.communicate(input)<br> <br> # If the child process failed and we were asked to raise an exception, do so<br> if raiseOnError == True and proc.returncode != 0:<br> raise Exception(<br> 'child process ' + str(command) +<br> ' failed with exit code ' + str(proc.returncode) +<br> '\nstdout: "' + stdout + '"' +<br> '\nstderr: "' + stderr + '"'<br> )<br> <br> return CommandOutput(proc.returncode, stdout, stderr)</code> | |
|
|
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: |
|
|
```json |
|
|
{ |
|
|
"scale": 20.0, |
|
|
"similarity_fct": "cos_sim" |
|
|
} |
|
|
``` |
|
|
|
|
|
### Evaluation Dataset |
|
|
|
|
|
#### code_search_net |
|
|
|
|
|
* Dataset: code_search_net |
|
|
* Size: 23,107 evaluation samples |
|
|
* Columns: <code>query</code> and <code>positive</code> |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | query | positive | |
|
|
|:--------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------| |
|
|
| type | string | string | |
|
|
| details | <ul><li>min: 5 tokens</li><li>mean: 168.27 tokens</li><li>max: 2118 tokens</li></ul> | <ul><li>min: 48 tokens</li><li>mean: 467.9 tokens</li><li>max: 4096 tokens</li></ul> | |
|
|
* Samples: |
|
|
| query | positive | |
|
|
|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
|
|
| <code>Train a deepq model.<br><br> Parameters<br> -------<br> env: gym.Env<br> environment to train on<br> network: string or a function<br> neural network to use as a q function approximator. If string, has to be one of the names of registered models in baselines.common.models<br> (mlp, cnn, conv_only). If a function, should take an observation tensor and return a latent variable tensor, which<br> will be mapped to the Q function heads (see build_q_func in baselines.deepq.models for details on that)<br> seed: int or None<br> prng seed. The runs with the same seed "should" give the same results. If None, no seeding is used.<br> lr: float<br> learning rate for adam optimizer<br> total_timesteps: int<br> number of env steps to optimizer for<br> buffer_size: int<br> size of the replay buffer<br> exploration_fraction: float<br> fraction of entire training period over which the exploration rate is annealed<br> exploration_final_eps: float<br> final value of ra...</code> | <code>def learn(env,<br> network,<br> seed=None,<br> lr=5e-4,<br> total_timesteps=100000,<br> buffer_size=50000,<br> exploration_fraction=0.1,<br> exploration_final_eps=0.02,<br> train_freq=1,<br> batch_size=32,<br> print_freq=100,<br> checkpoint_freq=10000,<br> checkpoint_path=None,<br> learning_starts=1000,<br> gamma=1.0,<br> target_network_update_freq=500,<br> prioritized_replay=False,<br> prioritized_replay_alpha=0.6,<br> prioritized_replay_beta0=0.4,<br> prioritized_replay_beta_iters=None,<br> prioritized_replay_eps=1e-6,<br> param_noise=False,<br> callback=None,<br> load_path=None,<br> **network_kwargs<br> ):<br> """Train a deepq model.<br><br> Parameters<br> -------<br> env: gym.Env<br> environment to train on<br> network: string or a function<br> neural network to use as a q function approximator. If string, has to be one of the ...</code> | |
|
|
| <code>Save model to a pickle located at `path`</code> | <code>def save_act(self, path=None):<br> """Save model to a pickle located at `path`"""<br> if path is None:<br> path = os.path.join(logger.get_dir(), "model.pkl")<br><br> with tempfile.TemporaryDirectory() as td:<br> save_variables(os.path.join(td, "model"))<br> arc_name = os.path.join(td, "packed.zip")<br> with zipfile.ZipFile(arc_name, 'w') as zipf:<br> for root, dirs, files in os.walk(td):<br> for fname in files:<br> file_path = os.path.join(root, fname)<br> if file_path != arc_name:<br> zipf.write(file_path, os.path.relpath(file_path, td))<br> with open(arc_name, "rb") as f:<br> model_data = f.read()<br> with open(path, "wb") as f:<br> cloudpickle.dump((model_data, self._act_params), f)</code> | |
|
|
| <code>CNN from Nature paper.</code> | <code>def nature_cnn(unscaled_images, **conv_kwargs):<br> """<br> CNN from Nature paper.<br> """<br> scaled_images = tf.cast(unscaled_images, tf.float32) / 255.<br> activ = tf.nn.relu<br> h = activ(conv(scaled_images, 'c1', nf=32, rf=8, stride=4, init_scale=np.sqrt(2),<br> **conv_kwargs))<br> h2 = activ(conv(h, 'c2', nf=64, rf=4, stride=2, init_scale=np.sqrt(2), **conv_kwargs))<br> h3 = activ(conv(h2, 'c3', nf=64, rf=3, stride=1, init_scale=np.sqrt(2), **conv_kwargs))<br> h3 = conv_to_fc(h3)<br> return activ(fc(h3, 'fc1', nh=512, init_scale=np.sqrt(2)))</code> | |
|
|
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: |
|
|
```json |
|
|
{ |
|
|
"scale": 20.0, |
|
|
"similarity_fct": "cos_sim" |
|
|
} |
|
|
``` |
|
|
|
|
|
### Training Hyperparameters |
|
|
#### Non-Default Hyperparameters |
|
|
|
|
|
- `eval_strategy`: epoch |
|
|
- `per_device_train_batch_size`: 4 |
|
|
- `gradient_accumulation_steps`: 4 |
|
|
- `learning_rate`: 2e-05 |
|
|
- `num_train_epochs`: 10 |
|
|
- `warmup_steps`: 1000 |
|
|
- `fp16`: True |
|
|
|
|
|
#### All Hyperparameters |
|
|
<details><summary>Click to expand</summary> |
|
|
|
|
|
- `overwrite_output_dir`: False |
|
|
- `do_predict`: False |
|
|
- `eval_strategy`: epoch |
|
|
- `prediction_loss_only`: True |
|
|
- `per_device_train_batch_size`: 4 |
|
|
- `per_device_eval_batch_size`: 8 |
|
|
- `per_gpu_train_batch_size`: None |
|
|
- `per_gpu_eval_batch_size`: None |
|
|
- `gradient_accumulation_steps`: 4 |
|
|
- `eval_accumulation_steps`: None |
|
|
- `torch_empty_cache_steps`: None |
|
|
- `learning_rate`: 2e-05 |
|
|
- `weight_decay`: 0.0 |
|
|
- `adam_beta1`: 0.9 |
|
|
- `adam_beta2`: 0.999 |
|
|
- `adam_epsilon`: 1e-08 |
|
|
- `max_grad_norm`: 1.0 |
|
|
- `num_train_epochs`: 10 |
|
|
- `max_steps`: -1 |
|
|
- `lr_scheduler_type`: linear |
|
|
- `lr_scheduler_kwargs`: {} |
|
|
- `warmup_ratio`: 0.0 |
|
|
- `warmup_steps`: 1000 |
|
|
- `log_level`: passive |
|
|
- `log_level_replica`: warning |
|
|
- `log_on_each_node`: True |
|
|
- `logging_nan_inf_filter`: True |
|
|
- `save_safetensors`: True |
|
|
- `save_on_each_node`: False |
|
|
- `save_only_model`: False |
|
|
- `restore_callback_states_from_checkpoint`: False |
|
|
- `no_cuda`: False |
|
|
- `use_cpu`: False |
|
|
- `use_mps_device`: False |
|
|
- `seed`: 42 |
|
|
- `data_seed`: None |
|
|
- `jit_mode_eval`: False |
|
|
- `use_ipex`: False |
|
|
- `bf16`: False |
|
|
- `fp16`: True |
|
|
- `fp16_opt_level`: O1 |
|
|
- `half_precision_backend`: auto |
|
|
- `bf16_full_eval`: False |
|
|
- `fp16_full_eval`: False |
|
|
- `tf32`: None |
|
|
- `local_rank`: 0 |
|
|
- `ddp_backend`: None |
|
|
- `tpu_num_cores`: None |
|
|
- `tpu_metrics_debug`: False |
|
|
- `debug`: [] |
|
|
- `dataloader_drop_last`: False |
|
|
- `dataloader_num_workers`: 0 |
|
|
- `dataloader_prefetch_factor`: None |
|
|
- `past_index`: -1 |
|
|
- `disable_tqdm`: False |
|
|
- `remove_unused_columns`: True |
|
|
- `label_names`: None |
|
|
- `load_best_model_at_end`: False |
|
|
- `ignore_data_skip`: False |
|
|
- `fsdp`: [] |
|
|
- `fsdp_min_num_params`: 0 |
|
|
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} |
|
|
- `fsdp_transformer_layer_cls_to_wrap`: None |
|
|
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} |
|
|
- `deepspeed`: None |
|
|
- `label_smoothing_factor`: 0.0 |
|
|
- `optim`: adamw_torch |
|
|
- `optim_args`: None |
|
|
- `adafactor`: False |
|
|
- `group_by_length`: False |
|
|
- `length_column_name`: length |
|
|
- `ddp_find_unused_parameters`: None |
|
|
- `ddp_bucket_cap_mb`: None |
|
|
- `ddp_broadcast_buffers`: False |
|
|
- `dataloader_pin_memory`: True |
|
|
- `dataloader_persistent_workers`: False |
|
|
- `skip_memory_metrics`: True |
|
|
- `use_legacy_prediction_loop`: False |
|
|
- `push_to_hub`: False |
|
|
- `resume_from_checkpoint`: None |
|
|
- `hub_model_id`: None |
|
|
- `hub_strategy`: every_save |
|
|
- `hub_private_repo`: None |
|
|
- `hub_always_push`: False |
|
|
- `gradient_checkpointing`: False |
|
|
- `gradient_checkpointing_kwargs`: None |
|
|
- `include_inputs_for_metrics`: False |
|
|
- `include_for_metrics`: [] |
|
|
- `eval_do_concat_batches`: True |
|
|
- `fp16_backend`: auto |
|
|
- `push_to_hub_model_id`: None |
|
|
- `push_to_hub_organization`: None |
|
|
- `mp_parameters`: |
|
|
- `auto_find_batch_size`: False |
|
|
- `full_determinism`: False |
|
|
- `torchdynamo`: None |
|
|
- `ray_scope`: last |
|
|
- `ddp_timeout`: 1800 |
|
|
- `torch_compile`: False |
|
|
- `torch_compile_backend`: None |
|
|
- `torch_compile_mode`: None |
|
|
- `dispatch_batches`: None |
|
|
- `split_batches`: None |
|
|
- `include_tokens_per_second`: False |
|
|
- `include_num_input_tokens_seen`: False |
|
|
- `neftune_noise_alpha`: None |
|
|
- `optim_target_modules`: None |
|
|
- `batch_eval_metrics`: False |
|
|
- `eval_on_start`: False |
|
|
- `use_liger_kernel`: False |
|
|
- `eval_use_gather_object`: False |
|
|
- `average_tokens_across_devices`: False |
|
|
- `prompts`: None |
|
|
- `batch_sampler`: batch_sampler |
|
|
- `multi_dataset_batch_sampler`: proportional |
|
|
|
|
|
</details> |
|
|
|
|
|
### Training Logs |
|
|
<details><summary>Click to expand</summary> |
|
|
|
|
|
| Epoch | Step | Training Loss | Validation Loss | |
|
|
|:------:|:-----:|:-------------:|:---------------:| |
|
|
| 0.0078 | 200 | 0.634 | - | |
|
|
| 0.0155 | 400 | 0.0046 | - | |
|
|
| 0.0233 | 600 | 0.0009 | - | |
|
|
| 0.0311 | 800 | 0.0004 | - | |
|
|
| 0.0388 | 1000 | 0.0001 | - | |
|
|
| 0.0466 | 1200 | 0.0002 | - | |
|
|
| 0.0543 | 1400 | 0.0001 | - | |
|
|
| 0.0621 | 1600 | 0.0001 | - | |
|
|
| 0.0699 | 1800 | 0.0001 | - | |
|
|
| 0.0776 | 2000 | 0.0 | - | |
|
|
| 0.0854 | 2200 | 0.0 | - | |
|
|
| 0.0932 | 2400 | 0.0 | - | |
|
|
| 0.1009 | 2600 | 0.0 | - | |
|
|
| 0.1087 | 2800 | 0.0005 | - | |
|
|
| 0.1165 | 3000 | 0.0005 | - | |
|
|
| 0.1242 | 3200 | 0.0002 | - | |
|
|
| 0.1320 | 3400 | 0.0 | - | |
|
|
| 0.1397 | 3600 | 0.0 | - | |
|
|
| 0.1475 | 3800 | 0.0 | - | |
|
|
| 0.1553 | 4000 | 0.0001 | - | |
|
|
| 0.1630 | 4200 | 0.0 | - | |
|
|
| 0.1708 | 4400 | 0.0001 | - | |
|
|
| 0.1786 | 4600 | 0.0001 | - | |
|
|
| 0.1863 | 4800 | 0.0 | - | |
|
|
| 0.1941 | 5000 | 0.0 | - | |
|
|
| 0.2019 | 5200 | 0.0 | - | |
|
|
| 0.2096 | 5400 | 0.0 | - | |
|
|
| 0.2174 | 5600 | 0.0 | - | |
|
|
| 0.2251 | 5800 | 0.0 | - | |
|
|
| 0.2329 | 6000 | 0.0004 | - | |
|
|
| 0.2407 | 6200 | 0.0 | - | |
|
|
| 0.2484 | 6400 | 0.0001 | - | |
|
|
| 0.2562 | 6600 | 0.0 | - | |
|
|
| 0.2640 | 6800 | 0.0 | - | |
|
|
| 0.2717 | 7000 | 0.0 | - | |
|
|
| 0.2795 | 7200 | 0.0 | - | |
|
|
| 0.2873 | 7400 | 0.0 | - | |
|
|
| 0.2950 | 7600 | 0.0 | - | |
|
|
| 0.3028 | 7800 | 0.0 | - | |
|
|
| 0.3105 | 8000 | 0.0 | - | |
|
|
| 0.3183 | 8200 | 0.0 | - | |
|
|
| 0.3261 | 8400 | 0.0004 | - | |
|
|
| 0.3338 | 8600 | 0.0 | - | |
|
|
| 0.3416 | 8800 | 0.0 | - | |
|
|
| 0.3494 | 9000 | 0.0 | - | |
|
|
| 0.3571 | 9200 | 0.0 | - | |
|
|
| 0.3649 | 9400 | 0.0 | - | |
|
|
| 0.3727 | 9600 | 0.0 | - | |
|
|
| 0.3804 | 9800 | 0.0 | - | |
|
|
| 0.3882 | 10000 | 0.0 | - | |
|
|
| 0.3959 | 10200 | 0.0 | - | |
|
|
| 0.4037 | 10400 | 0.0 | - | |
|
|
| 0.4115 | 10600 | 0.0 | - | |
|
|
| 0.4192 | 10800 | 0.0 | - | |
|
|
| 0.4270 | 11000 | 0.0 | - | |
|
|
| 0.4348 | 11200 | 0.0 | - | |
|
|
| 0.4425 | 11400 | 0.0 | - | |
|
|
| 0.4503 | 11600 | 0.0 | - | |
|
|
| 0.4581 | 11800 | 0.0 | - | |
|
|
| 0.4658 | 12000 | 0.0 | - | |
|
|
| 0.4736 | 12200 | 0.0 | - | |
|
|
| 0.4813 | 12400 | 0.0 | - | |
|
|
| 0.4891 | 12600 | 0.0005 | - | |
|
|
| 0.4969 | 12800 | 0.0 | - | |
|
|
| 0.5046 | 13000 | 0.0 | - | |
|
|
| 0.5124 | 13200 | 0.0001 | - | |
|
|
| 0.5202 | 13400 | 0.0 | - | |
|
|
| 0.5279 | 13600 | 0.0 | - | |
|
|
| 0.5357 | 13800 | 0.0 | - | |
|
|
| 0.5435 | 14000 | 0.0 | - | |
|
|
| 0.5512 | 14200 | 0.0 | - | |
|
|
| 0.5590 | 14400 | 0.0004 | - | |
|
|
| 0.5667 | 14600 | 0.0 | - | |
|
|
| 0.5745 | 14800 | 0.0 | - | |
|
|
| 0.5823 | 15000 | 0.0 | - | |
|
|
| 0.5900 | 15200 | 0.0 | - | |
|
|
| 0.5978 | 15400 | 0.0 | - | |
|
|
| 0.6056 | 15600 | 0.0 | - | |
|
|
| 0.6133 | 15800 | 0.0 | - | |
|
|
| 0.6211 | 16000 | 0.0 | - | |
|
|
| 0.6289 | 16200 | 0.0 | - | |
|
|
| 0.6366 | 16400 | 0.0006 | - | |
|
|
| 0.6444 | 16600 | 0.0 | - | |
|
|
| 0.6521 | 16800 | 0.0005 | - | |
|
|
| 0.6599 | 17000 | 0.0 | - | |
|
|
| 0.6677 | 17200 | 0.0 | - | |
|
|
| 0.6754 | 17400 | 0.0 | - | |
|
|
| 0.6832 | 17600 | 0.0 | - | |
|
|
| 0.6910 | 17800 | 0.0 | - | |
|
|
| 0.6987 | 18000 | 0.0005 | - | |
|
|
| 0.7065 | 18200 | 0.0001 | - | |
|
|
| 0.7143 | 18400 | 0.0 | - | |
|
|
| 0.7220 | 18600 | 0.0 | - | |
|
|
| 0.7298 | 18800 | 0.0 | - | |
|
|
| 0.7375 | 19000 | 0.0 | - | |
|
|
| 0.7453 | 19200 | 0.0 | - | |
|
|
| 0.7531 | 19400 | 0.0 | - | |
|
|
| 0.7608 | 19600 | 0.0 | - | |
|
|
| 0.7686 | 19800 | 0.0001 | - | |
|
|
| 0.7764 | 20000 | 0.0 | - | |
|
|
| 0.7841 | 20200 | 0.0 | - | |
|
|
| 0.7919 | 20400 | 0.0 | - | |
|
|
| 0.7997 | 20600 | 0.0004 | - | |
|
|
| 0.8074 | 20800 | 0.0 | - | |
|
|
| 0.8152 | 21000 | 0.0 | - | |
|
|
| 0.8229 | 21200 | 0.0 | - | |
|
|
| 0.8307 | 21400 | 0.0009 | - | |
|
|
| 0.8385 | 21600 | 0.0 | - | |
|
|
| 0.8462 | 21800 | 0.0 | - | |
|
|
| 0.8540 | 22000 | 0.0 | - | |
|
|
| 0.8618 | 22200 | 0.0 | - | |
|
|
| 0.8695 | 22400 | 0.0002 | - | |
|
|
| 0.8773 | 22600 | 0.0 | - | |
|
|
| 0.8851 | 22800 | 0.0 | - | |
|
|
| 0.8928 | 23000 | 0.0001 | - | |
|
|
| 0.9006 | 23200 | 0.0 | - | |
|
|
| 0.9083 | 23400 | 0.0 | - | |
|
|
| 0.9161 | 23600 | 0.0 | - | |
|
|
| 0.9239 | 23800 | 0.0 | - | |
|
|
| 0.9316 | 24000 | 0.0 | - | |
|
|
| 0.9394 | 24200 | 0.0 | - | |
|
|
| 0.9472 | 24400 | 0.0 | - | |
|
|
| 0.9549 | 24600 | 0.0 | - | |
|
|
| 0.9627 | 24800 | 0.0 | - | |
|
|
| 0.9704 | 25000 | 0.0 | - | |
|
|
| 0.9782 | 25200 | 0.0 | - | |
|
|
| 0.9860 | 25400 | 0.0 | - | |
|
|
| 0.9937 | 25600 | 0.0 | - | |
|
|
| 1.0 | 25762 | - | 0.0001 | |
|
|
| 1.0015 | 25800 | 0.0005 | - | |
|
|
| 1.0092 | 26000 | 0.0 | - | |
|
|
| 1.0170 | 26200 | 0.0 | - | |
|
|
| 1.0248 | 26400 | 0.0 | - | |
|
|
| 1.0325 | 26600 | 0.0 | - | |
|
|
| 1.0403 | 26800 | 0.0 | - | |
|
|
| 1.0481 | 27000 | 0.0 | - | |
|
|
| 1.0558 | 27200 | 0.0 | - | |
|
|
| 1.0636 | 27400 | 0.0 | - | |
|
|
| 1.0713 | 27600 | 0.0 | - | |
|
|
| 1.0791 | 27800 | 0.0 | - | |
|
|
| 1.0869 | 28000 | 0.0 | - | |
|
|
| 1.0946 | 28200 | 0.0 | - | |
|
|
| 1.1024 | 28400 | 0.0 | - | |
|
|
| 1.1102 | 28600 | 0.0 | - | |
|
|
| 1.1179 | 28800 | 0.0 | - | |
|
|
| 1.1257 | 29000 | 0.0 | - | |
|
|
| 1.1335 | 29200 | 0.0 | - | |
|
|
| 1.1412 | 29400 | 0.0 | - | |
|
|
| 1.1490 | 29600 | 0.0 | - | |
|
|
| 1.1567 | 29800 | 0.0 | - | |
|
|
| 1.1645 | 30000 | 0.0 | - | |
|
|
| 1.1723 | 30200 | 0.0 | - | |
|
|
| 1.1800 | 30400 | 0.0 | - | |
|
|
| 1.1878 | 30600 | 0.0 | - | |
|
|
| 1.1956 | 30800 | 0.0 | - | |
|
|
| 1.2033 | 31000 | 0.0 | - | |
|
|
| 1.2111 | 31200 | 0.0 | - | |
|
|
| 1.2189 | 31400 | 0.0 | - | |
|
|
| 1.2266 | 31600 | 0.0004 | - | |
|
|
| 1.2344 | 31800 | 0.0004 | - | |
|
|
| 1.2421 | 32000 | 0.0 | - | |
|
|
| 1.2499 | 32200 | 0.0 | - | |
|
|
| 1.2577 | 32400 | 0.0 | - | |
|
|
| 1.2654 | 32600 | 0.0 | - | |
|
|
| 1.2732 | 32800 | 0.0 | - | |
|
|
| 1.2810 | 33000 | 0.0 | - | |
|
|
| 1.2887 | 33200 | 0.0 | - | |
|
|
| 1.2965 | 33400 | 0.0 | - | |
|
|
| 1.3043 | 33600 | 0.0 | - | |
|
|
| 1.3120 | 33800 | 0.0 | - | |
|
|
| 1.3198 | 34000 | 0.0 | - | |
|
|
| 1.3275 | 34200 | 0.0 | - | |
|
|
| 1.3353 | 34400 | 0.0 | - | |
|
|
| 1.3431 | 34600 | 0.0 | - | |
|
|
| 1.3508 | 34800 | 0.0004 | - | |
|
|
| 1.3586 | 35000 | 0.0005 | - | |
|
|
| 1.3664 | 35200 | 0.0004 | - | |
|
|
| 1.3741 | 35400 | 0.0011 | - | |
|
|
| 1.3819 | 35600 | 0.0 | - | |
|
|
| 1.3897 | 35800 | 0.0 | - | |
|
|
| 1.3974 | 36000 | 0.0 | - | |
|
|
| 1.4052 | 36200 | 0.0 | - | |
|
|
| 1.4129 | 36400 | 0.0 | - | |
|
|
| 1.4207 | 36600 | 0.0 | - | |
|
|
| 1.4285 | 36800 | 0.0 | - | |
|
|
| 1.4362 | 37000 | 0.0 | - | |
|
|
| 1.4440 | 37200 | 0.0001 | - | |
|
|
| 1.4518 | 37400 | 0.0 | - | |
|
|
| 1.4595 | 37600 | 0.0 | - | |
|
|
| 1.4673 | 37800 | 0.0 | - | |
|
|
| 1.4751 | 38000 | 0.0 | - | |
|
|
| 1.4828 | 38200 | 0.0004 | - | |
|
|
| 1.4906 | 38400 | 0.0003 | - | |
|
|
| 1.4983 | 38600 | 0.0 | - | |
|
|
| 1.5061 | 38800 | 0.0 | - | |
|
|
| 1.5139 | 39000 | 0.0 | - | |
|
|
| 1.5216 | 39200 | 0.0 | - | |
|
|
| 1.5294 | 39400 | 0.0004 | - | |
|
|
| 1.5372 | 39600 | 0.0004 | - | |
|
|
| 1.5449 | 39800 | 0.0 | - | |
|
|
| 1.5527 | 40000 | 0.0 | - | |
|
|
| 1.5605 | 40200 | 0.0 | - | |
|
|
| 1.5682 | 40400 | 0.0 | - | |
|
|
| 1.5760 | 40600 | 0.0009 | - | |
|
|
| 1.5837 | 40800 | 0.0 | - | |
|
|
| 1.5915 | 41000 | 0.0009 | - | |
|
|
| 1.5993 | 41200 | 0.0 | - | |
|
|
| 1.6070 | 41400 | 0.0 | - | |
|
|
| 1.6148 | 41600 | 0.0 | - | |
|
|
| 1.6226 | 41800 | 0.0 | - | |
|
|
| 1.6303 | 42000 | 0.0 | - | |
|
|
| 1.6381 | 42200 | 0.0 | - | |
|
|
| 1.6459 | 42400 | 0.0 | - | |
|
|
| 1.6536 | 42600 | 0.0 | - | |
|
|
| 1.6614 | 42800 | 0.0 | - | |
|
|
| 1.6691 | 43000 | 0.0 | - | |
|
|
| 1.6769 | 43200 | 0.0 | - | |
|
|
| 1.6847 | 43400 | 0.0 | - | |
|
|
| 1.6924 | 43600 | 0.0 | - | |
|
|
| 1.7002 | 43800 | 0.0 | - | |
|
|
| 1.7080 | 44000 | 0.0 | - | |
|
|
| 1.7157 | 44200 | 0.0 | - | |
|
|
| 1.7235 | 44400 | 0.0 | - | |
|
|
| 1.7313 | 44600 | 0.0 | - | |
|
|
| 1.7390 | 44800 | 0.0 | - | |
|
|
| 1.7468 | 45000 | 0.0 | - | |
|
|
| 1.7545 | 45200 | 0.0 | - | |
|
|
| 1.7623 | 45400 | 0.0 | - | |
|
|
| 1.7701 | 45600 | 0.0 | - | |
|
|
| 1.7778 | 45800 | 0.0 | - | |
|
|
| 1.7856 | 46000 | 0.0 | - | |
|
|
| 1.7934 | 46200 | 0.0 | - | |
|
|
| 1.8011 | 46400 | 0.0 | - | |
|
|
| 1.8089 | 46600 | 0.0 | - | |
|
|
| 1.8167 | 46800 | 0.0 | - | |
|
|
| 1.8244 | 47000 | 0.0 | - | |
|
|
| 1.8322 | 47200 | 0.0 | - | |
|
|
| 1.8399 | 47400 | 0.0 | - | |
|
|
| 1.8477 | 47600 | 0.0 | - | |
|
|
| 1.8555 | 47800 | 0.0004 | - | |
|
|
| 1.8632 | 48000 | 0.0 | - | |
|
|
| 1.8710 | 48200 | 0.0 | - | |
|
|
| 1.8788 | 48400 | 0.0 | - | |
|
|
| 1.8865 | 48600 | 0.0 | - | |
|
|
| 1.8943 | 48800 | 0.0 | - | |
|
|
| 1.9021 | 49000 | 0.0004 | - | |
|
|
| 1.9098 | 49200 | 0.0 | - | |
|
|
| 1.9176 | 49400 | 0.0 | - | |
|
|
| 1.9253 | 49600 | 0.0004 | - | |
|
|
| 1.9331 | 49800 | 0.0 | - | |
|
|
| 1.9409 | 50000 | 0.0 | - | |
|
|
| 1.9486 | 50200 | 0.0 | - | |
|
|
| 1.9564 | 50400 | 0.0 | - | |
|
|
| 1.9642 | 50600 | 0.0004 | - | |
|
|
| 1.9719 | 50800 | 0.0 | - | |
|
|
| 1.9797 | 51000 | 0.0 | - | |
|
|
| 1.9875 | 51200 | 0.0 | - | |
|
|
| 1.9952 | 51400 | 0.0004 | - | |
|
|
| 2.0 | 51524 | - | 0.0001 | |
|
|
| 2.0030 | 51600 | 0.0 | - | |
|
|
| 2.0107 | 51800 | 0.0 | - | |
|
|
| 2.0185 | 52000 | 0.0 | - | |
|
|
| 2.0262 | 52200 | 0.0 | - | |
|
|
| 2.0340 | 52400 | 0.0004 | - | |
|
|
| 2.0418 | 52600 | 0.0004 | - | |
|
|
| 2.0495 | 52800 | 0.0 | - | |
|
|
| 2.0573 | 53000 | 0.0008 | - | |
|
|
| 2.0651 | 53200 | 0.0 | - | |
|
|
| 2.0728 | 53400 | 0.0 | - | |
|
|
| 2.0806 | 53600 | 0.0 | - | |
|
|
| 2.0883 | 53800 | 0.0 | - | |
|
|
| 2.0961 | 54000 | 0.0 | - | |
|
|
| 2.1039 | 54200 | 0.0 | - | |
|
|
| 2.1116 | 54400 | 0.0 | - | |
|
|
| 2.1194 | 54600 | 0.0 | - | |
|
|
| 2.1272 | 54800 | 0.0 | - | |
|
|
| 2.1349 | 55000 | 0.0 | - | |
|
|
| 2.1427 | 55200 | 0.0 | - | |
|
|
| 2.1505 | 55400 | 0.0 | - | |
|
|
| 2.1582 | 55600 | 0.0 | - | |
|
|
| 2.1660 | 55800 | 0.0 | - | |
|
|
| 2.1737 | 56000 | 0.0 | - | |
|
|
| 2.1815 | 56200 | 0.0 | - | |
|
|
| 2.1893 | 56400 | 0.0 | - | |
|
|
| 2.1970 | 56600 | 0.0 | - | |
|
|
| 2.2048 | 56800 | 0.0 | - | |
|
|
| 2.2126 | 57000 | 0.0 | - | |
|
|
| 2.2203 | 57200 | 0.0 | - | |
|
|
| 2.2281 | 57400 | 0.0 | - | |
|
|
| 2.2359 | 57600 | 0.0 | - | |
|
|
| 2.2436 | 57800 | 0.0 | - | |
|
|
| 2.2514 | 58000 | 0.0004 | - | |
|
|
| 2.2591 | 58200 | 0.0 | - | |
|
|
| 2.2669 | 58400 | 0.0004 | - | |
|
|
| 2.2747 | 58600 | 0.0 | - | |
|
|
| 2.2824 | 58800 | 0.0 | - | |
|
|
| 2.2902 | 59000 | 0.0 | - | |
|
|
| 2.2980 | 59200 | 0.0 | - | |
|
|
| 2.3057 | 59400 | 0.0 | - | |
|
|
| 2.3135 | 59600 | 0.0 | - | |
|
|
| 2.3213 | 59800 | 0.0004 | - | |
|
|
| 2.3290 | 60000 | 0.0 | - | |
|
|
| 2.3368 | 60200 | 0.0004 | - | |
|
|
| 2.3445 | 60400 | 0.0 | - | |
|
|
| 2.3523 | 60600 | 0.0 | - | |
|
|
| 2.3601 | 60800 | 0.0 | - | |
|
|
| 2.3678 | 61000 | 0.0 | - | |
|
|
| 2.3756 | 61200 | 0.0 | - | |
|
|
| 2.3834 | 61400 | 0.0 | - | |
|
|
| 2.3911 | 61600 | 0.0 | - | |
|
|
| 2.3989 | 61800 | 0.0 | - | |
|
|
| 2.4067 | 62000 | 0.0005 | - | |
|
|
| 2.4144 | 62200 | 0.0 | - | |
|
|
| 2.4222 | 62400 | 0.0 | - | |
|
|
| 2.4299 | 62600 | 0.0 | - | |
|
|
| 2.4377 | 62800 | 0.0 | - | |
|
|
| 2.4455 | 63000 | 0.0 | - | |
|
|
| 2.4532 | 63200 | 0.0 | - | |
|
|
| 2.4610 | 63400 | 0.0 | - | |
|
|
| 2.4688 | 63600 | 0.0 | - | |
|
|
| 2.4765 | 63800 | 0.0 | - | |
|
|
| 2.4843 | 64000 | 0.0 | - | |
|
|
| 2.4921 | 64200 | 0.0 | - | |
|
|
| 2.4998 | 64400 | 0.0 | - | |
|
|
| 2.5076 | 64600 | 0.0 | - | |
|
|
| 2.5153 | 64800 | 0.0 | - | |
|
|
| 2.5231 | 65000 | 0.0 | - | |
|
|
| 2.5309 | 65200 | 0.0 | - | |
|
|
| 2.5386 | 65400 | 0.0 | - | |
|
|
| 2.5464 | 65600 | 0.0004 | - | |
|
|
| 2.5542 | 65800 | 0.0 | - | |
|
|
| 2.5619 | 66000 | 0.0 | - | |
|
|
| 2.5697 | 66200 | 0.0 | - | |
|
|
| 2.5775 | 66400 | 0.0 | - | |
|
|
| 2.5852 | 66600 | 0.0 | - | |
|
|
| 2.5930 | 66800 | 0.0 | - | |
|
|
| 2.6007 | 67000 | 0.0 | - | |
|
|
| 2.6085 | 67200 | 0.0 | - | |
|
|
| 2.6163 | 67400 | 0.0 | - | |
|
|
| 2.6240 | 67600 | 0.0 | - | |
|
|
| 2.6318 | 67800 | 0.0 | - | |
|
|
| 2.6396 | 68000 | 0.0 | - | |
|
|
| 2.6473 | 68200 | 0.0 | - | |
|
|
| 2.6551 | 68400 | 0.0 | - | |
|
|
| 2.6629 | 68600 | 0.0 | - | |
|
|
| 2.6706 | 68800 | 0.0004 | - | |
|
|
| 2.6784 | 69000 | 0.0 | - | |
|
|
| 2.6861 | 69200 | 0.0 | - | |
|
|
| 2.6939 | 69400 | 0.0 | - | |
|
|
| 2.7017 | 69600 | 0.0004 | - | |
|
|
| 2.7094 | 69800 | 0.0004 | - | |
|
|
| 2.7172 | 70000 | 0.0 | - | |
|
|
| 2.7250 | 70200 | 0.0 | - | |
|
|
| 2.7327 | 70400 | 0.0 | - | |
|
|
| 2.7405 | 70600 | 0.0 | - | |
|
|
| 2.7483 | 70800 | 0.0 | - | |
|
|
| 2.7560 | 71000 | 0.0004 | - | |
|
|
| 2.7638 | 71200 | 0.0 | - | |
|
|
| 2.7715 | 71400 | 0.0 | - | |
|
|
| 2.7793 | 71600 | 0.0 | - | |
|
|
| 2.7871 | 71800 | 0.0 | - | |
|
|
| 2.7948 | 72000 | 0.0 | - | |
|
|
| 2.8026 | 72200 | 0.0 | - | |
|
|
| 2.8104 | 72400 | 0.0 | - | |
|
|
| 2.8181 | 72600 | 0.0 | - | |
|
|
| 2.8259 | 72800 | 0.0 | - | |
|
|
| 2.8337 | 73000 | 0.0004 | - | |
|
|
| 2.8414 | 73200 | 0.0 | - | |
|
|
| 2.8492 | 73400 | 0.0 | - | |
|
|
| 2.8569 | 73600 | 0.0 | - | |
|
|
| 2.8647 | 73800 | 0.0004 | - | |
|
|
| 2.8725 | 74000 | 0.0 | - | |
|
|
| 2.8802 | 74200 | 0.0 | - | |
|
|
| 2.8880 | 74400 | 0.0 | - | |
|
|
| 2.8958 | 74600 | 0.0 | - | |
|
|
| 2.9035 | 74800 | 0.0 | - | |
|
|
| 2.9113 | 75000 | 0.0 | - | |
|
|
| 2.9191 | 75200 | 0.0 | - | |
|
|
| 2.9268 | 75400 | 0.0004 | - | |
|
|
| 2.9346 | 75600 | 0.0 | - | |
|
|
| 2.9423 | 75800 | 0.0 | - | |
|
|
| 2.9501 | 76000 | 0.0 | - | |
|
|
| 2.9579 | 76200 | 0.0 | - | |
|
|
| 2.9656 | 76400 | 0.0 | - | |
|
|
| 2.9734 | 76600 | 0.0004 | - | |
|
|
| 2.9812 | 76800 | 0.0 | - | |
|
|
| 2.9889 | 77000 | 0.0 | - | |
|
|
| 2.9967 | 77200 | 0.0 | - | |
|
|
| 3.0 | 77286 | - | 0.0000 | |
|
|
|
|
|
</details> |
|
|
|
|
|
### Framework Versions |
|
|
- Python: 3.11.11 |
|
|
- Sentence Transformers: 3.3.1 |
|
|
- Transformers: 4.48.0 |
|
|
- PyTorch: 2.5.1+cu121 |
|
|
- Accelerate: 1.2.1 |
|
|
- Datasets: 3.2.0 |
|
|
- Tokenizers: 0.21.0 |
|
|
|
|
|
## Citation |
|
|
|
|
|
### BibTeX |
|
|
|
|
|
#### ModernBERT |
|
|
```bibtex |
|
|
@misc{warner2024smarterbetterfasterlonger, |
|
|
title={Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference}, |
|
|
author={Benjamin Warner and Antoine Chaffin and Benjamin Clavié and Orion Weller and Oskar Hallström and Said Taghadouini and Alexis Gallagher and Raja Biswas and Faisal Ladhak and Tom Aarsen and Nathan Cooper and Griffin Adams and Jeremy Howard and Iacopo Poli}, |
|
|
year={2024}, |
|
|
eprint={2412.13663}, |
|
|
archivePrefix={arXiv}, |
|
|
primaryClass={cs.CL}, |
|
|
url={https://arxiv.org/abs/2412.13663}, |
|
|
} |
|
|
``` |
|
|
|
|
|
#### Sentence Transformers |
|
|
```bibtex |
|
|
@inproceedings{reimers-2019-sentence-bert, |
|
|
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", |
|
|
author = "Reimers, Nils and Gurevych, Iryna", |
|
|
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", |
|
|
month = "11", |
|
|
year = "2019", |
|
|
publisher = "Association for Computational Linguistics", |
|
|
url = "https://arxiv.org/abs/1908.10084", |
|
|
} |
|
|
``` |
|
|
|
|
|
#### MultipleNegativesRankingLoss |
|
|
```bibtex |
|
|
@misc{henderson2017efficient, |
|
|
title={Efficient Natural Language Response Suggestion for Smart Reply}, |
|
|
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil}, |
|
|
year={2017}, |
|
|
eprint={1705.00652}, |
|
|
archivePrefix={arXiv}, |
|
|
primaryClass={cs.CL} |
|
|
} |
|
|
``` |
|
|
|
|
|
<!-- |
|
|
## Glossary |
|
|
|
|
|
*Clearly define terms in order to be accessible across audiences.* |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
## Model Card Authors |
|
|
|
|
|
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
## Model Card Contact |
|
|
|
|
|
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* |
|
|
--> |
