Upload 10 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "bigscience/bloomz-560m",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLMSimulMT"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "seq_length": 2048,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.1",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250681
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.34.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3a736720d95ba8bd0a30613ae46c36a84cd21335d44c6ebd7ec5bbad305e4de
+size 1118121246

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeaf6a4cf6472e27e1a44e1c97d1a03d1b70b487d9fd6474cd2642fe21eecc8f
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff16aff41c883e654a23b2d7872fe65c1d4f9ffd52228b05982b4adda1b64873
+size 1064

special_tokens_map.json

@@ -0,0 +1,12 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54f80388e55d7d18f8caab6f55ccb39dab31d696d1726564e91fe74459b6c6f2
+size 14500653

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250680": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "tokenizer_class": "BloomTokenizer",
+  "trust_remove_code": true,
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,117 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9241341396371632,
+  "eval_steps": 1000,
+  "global_step": 7000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00011454256850621083,
+      "loss": 1.5582,
+      "step": 1000
+    },
+    {
+      "epoch": 0.27,
+      "eval_loss": 2.1084280014038086,
+      "eval_runtime": 3.7072,
+      "eval_samples_per_second": 240.072,
+      "eval_steps_per_second": 30.211,
+      "step": 1000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.099382692526634e-05,
+      "loss": 1.2078,
+      "step": 2000
+    },
+    {
+      "epoch": 0.55,
+      "eval_loss": 1.7273415327072144,
+      "eval_runtime": 3.6878,
+      "eval_samples_per_second": 241.334,
+      "eval_steps_per_second": 30.37,
+      "step": 2000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 6.613118276073197e-05,
+      "loss": 1.0718,
+      "step": 3000
+    },
+    {
+      "epoch": 0.82,
+      "eval_loss": 1.6304664611816406,
+      "eval_runtime": 3.687,
+      "eval_samples_per_second": 241.39,
+      "eval_steps_per_second": 30.377,
+      "step": 3000
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 5.7271284253105416e-05,
+      "loss": 0.9125,
+      "step": 4000
+    },
+    {
+      "epoch": 1.1,
+      "eval_loss": 1.5620102882385254,
+      "eval_runtime": 3.6964,
+      "eval_samples_per_second": 240.774,
+      "eval_steps_per_second": 30.3,
+      "step": 4000
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 5.1224993899462795e-05,
+      "loss": 0.7192,
+      "step": 5000
+    },
+    {
+      "epoch": 1.37,
+      "eval_loss": 1.5576059818267822,
+      "eval_runtime": 3.6938,
+      "eval_samples_per_second": 240.945,
+      "eval_steps_per_second": 30.321,
+      "step": 5000
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 4.676180777800049e-05,
+      "loss": 0.7183,
+      "step": 6000
+    },
+    {
+      "epoch": 1.65,
+      "eval_loss": 1.5256845951080322,
+      "eval_runtime": 3.6978,
+      "eval_samples_per_second": 240.681,
+      "eval_steps_per_second": 30.288,
+      "step": 6000
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 4.329302154257329e-05,
+      "loss": 0.716,
+      "step": 7000
+    },
+    {
+      "epoch": 1.92,
+      "eval_loss": 1.530071496963501,
+      "eval_runtime": 3.6992,
+      "eval_samples_per_second": 240.591,
+      "eval_steps_per_second": 30.277,
+      "step": 7000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 10914,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "total_flos": 5.261490028422758e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84a305c08093b6e784a8914dca2025b0771beaeb7f5a9755194979837345471f
+size 4600