Training in progress, step 6187

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

logs/distillation_objective=LinearObjective_l/events.out.tfevents.1723336715.715f24f8d8b8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2899d373208525189249aa7e2245702f21cadaf7522b8319cc69b81a56d1dd4
+size 40

logs/distillation_objective=LinearObjective_logits_weight_100__logits_loss_fn__function_kl_divergence_loss_at_0x7fc2b047b6d0___activations_weight_0__activations_loss_fn__function_mse_loss_at_0x7fc2b047b640/events.out.tfevents.1723339365.715f24f8d8b8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ffa3eb65dd1d89a025eed01ed2ce2946054b01d75b5727ec1bcca4ae69c65a0
+size 40

logs/distillation_objective=LinearObjective_logits_weight_10__logits_loss_fn__function_kl_divergence_loss_at_0x7fc2b047b6d0___activations_weight_0__activations_loss_fn__function_mse_loss_at_0x7fc2b047b640_/events.out.tfevents.1723339261.715f24f8d8b8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84b038286943bc2b8f308132b1a8aa3b714ab646a8727c8b30872e98f307d39a
+size 40

logs/distillation_objective=LinearObjective_logits_weight_1__logits_loss_fn__function_kl_divergence_loss_at_0x7f3fd8c9b6d0___activations_weight_0__activations_loss_fn__function_mse_loss_at_0x7f3fd8c9b640__/events.out.tfevents.1723338212.715f24f8d8b8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51cef175d3abe97b4133e10d9a56fe76fba37dab3ddf4443baf81b6d3f13f6b5
+size 40

logs/distillation_objective=LinearObjective_logits_weight_1__logits_loss_fn__function_kl_divergence_loss_at_0x7f731cc73760___activations_weight_0__activations_loss_fn__function_mse_loss_at_0x7f731cc736d0__/events.out.tfevents.1723338815.715f24f8d8b8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65506b9aeeaf3e4a8e60762ecbca2edfeb611ae3157da060a1a2a856192eee8e
+size 40

logs/distillation_objective=LinearObjective_logits_weight_1__logits_loss_fn__function_kl_divergence_loss_at_0x7fc2b047b6d0___activations_weight_0__activations_loss_fn__function_mse_loss_at_0x7fc2b047b640__/events.out.tfevents.1723339157.715f24f8d8b8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a7937f6ce52ea0f7b2aa7e8f295e139d7749ac25dd528b9296b749cbc15060
+size 40

logs/distillation_objective=LinearObjective_logits_weight_1__logits_loss_fn__function_kl_divergence_loss_at_0x7fc2b047b6d0___activations_weight_10__activations_loss_fn__function_kl_divergence_loss_at_0x7fc/events.out.tfevents.1723339780.715f24f8d8b8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0b55aa17ae825c62acc8c306af7a92936073824d1ec498faff6d0fee1cd50a6
+size 40

logs/distillation_objective=LinearObjective_logits_weight_1__logits_loss_fn__function_kl_divergence_loss_at_0x7fc2b047b6d0___activations_weight_10__activations_loss_fn__function_mse_loss_at_0x7fc2b047b640_/events.out.tfevents.1723339571.715f24f8d8b8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b48a4f1c1a098d12189ab0186698aabe940d16b37652cd21ec9181c20b1876df
+size 40

logs/distillation_objective=LinearObjective_logits_weight_1__logits_loss_fn__function_kl_divergence_loss_at_0x7fc2b047b6d0___activations_weight_1__activations_loss_fn__function_kl_divergence_loss_at_0x7fc2/events.out.tfevents.1723339675.715f24f8d8b8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cb05898808500756180b374402eb3de0a6018c2eaf14e2b2213b894663a9185
+size 40

logs/distillation_objective=LinearObjective_logits_weight_1__logits_loss_fn__function_kl_divergence_loss_at_0x7fc2b047b6d0___activations_weight_1__activations_loss_fn__function_mse_loss_at_0x7fc2b047b640__/events.out.tfevents.1723339469.715f24f8d8b8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af24f168a54bbd9dec485143e2b1478eca3477323f0f060d50aebc626a96907b
+size 40

logs/distillation_objective=_distily_objectiv/events.out.tfevents.1723336613.715f24f8d8b8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6f1981a2287a8236c04069adb69f21746136401693f09c81b8aeb363e06ed0d
+size 40

logs/distillation_objective=_distily_objectives_LegacyObjective_object_at_0x7f252bcd7fd0_/events.out.tfevents.1723340667.715f24f8d8b8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b928021ba4a3046595f051e9edd7e422d10f3081bedabb7894e6f73e6c2e463
+size 1317322

logs/distillation_objective=_distily_objectives_LegacyObjective_object_at_0x7f409f78ffd0_/events.out.tfevents.1723338102.715f24f8d8b8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff2a7a601f47a3eeda07781e4cf46f6ecb3ed30ccf1a55d45c491fa0e09becaf
+size 40

logs/distillation_objective=_distily_objectives_LegacyObjective_object_at_0x7f5276fc3fd0_/events.out.tfevents.1723336133.715f24f8d8b8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88574acc02bb058e97c11878343a61175b6f522187e75428e1cfb35be88c3ce6
+size 40

logs/distillation_objective=_distily_objectives_LegacyObjective_object_at_0x7f73e47d3fd0_/events.out.tfevents.1723338711.715f24f8d8b8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f3b476f9fd2175d0cda9e20aa153e7a7422140a78a3f4ddf0bf4e18c7dd9276
+size 40

logs/distillation_objective=_distily_objectives_LegacyObjective_object_at_0x7f85ee6f3fd0_/events.out.tfevents.1723335813.715f24f8d8b8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4447a4fde1d32eb1d086940b48c5de1284334c9696789df8f2d6083ae3436c81
+size 40

logs/distillation_objective=_distily_objectives_LegacyObjective_object_at_0x7fa72f603fd0_/events.out.tfevents.1723338479.715f24f8d8b8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0821bab35ab7862938fae3dc807e1ef36b00f1d2685013fb765050cc2ebcbc9b
+size 40

logs/distillation_objective=_distily_objectives_LegacyObjective_object_at_0x7fc377fa3fd0_/events.out.tfevents.1723339052.715f24f8d8b8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:832affff8711c8208e69b34d9724f06b99c00e630cebc5cf15e02fcff901f65f
+size 40

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d80539a190e414dc2b4b187153b272a72add71454d9ec4448e3f6bde1596fbc
+size 248894656

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa9da53f6c229b5661f0feb83da50bd76b3915ddfce90d6b94f61968f482226e
+size 907106628