Upload folder using huggingface_hub (#1)

- bdfb41d4ef0e06ce2524ea5a791ee6169faf0b7469ffeb38e65039632151847e (814365a256d22fa29c67b8d614ac902de74f506f)
- 06d10ef9901a7fdf4d08ad3bc76d68c6845fc1dd0a152905fff32a35be098dfd (d228a02bf51b9f2d3a7dad633b6ee3e448c4ae76)
- 8f040ff45e30b13c9807829aceee8d67849ad605e89dcb73aa3224f5e38ccd53 (bc27a286afe6013ef86e18354e420d9a1e2cc4ae)
- 5fc13fc990c47ee7d7c8162fa93abd0907e4ceb3322e2a63f3a0481ca00498fc (66d677f1d4ceec3e1c69b0c7e9a4e25ed641f07f)
- 6d9455dc259351a71d2a39ddcd813543fe3a582f06bc25b0a734501c9aadd755 (2ecce085d491968076824718c1f91be03271e485)
- f8df17b979991e819cfbeab9fe0b45bb1a7597b5f9a7fd9ab65384c29c93cc54 (938ed4b251a02890db6f1fdde7bc3932dcd9038b)
- 067afc33c0121524a881e842addf42e7117542bd2e652d711b2808e381e87fc1 (a08d8644ac7205269ccefc2eec8d52ba21460f5b)
- 112f138433f0ba5331bcd1d10edf735406d64cd61dc371442e8952a794fe24d9 (5a1a3dc1a368554e362d2b880114373b48f4e716)
- fb6bcb89333a63d8f988c4d1b82742074f4e5251d60a1f3d4e834f78c3b5c498 (321d439074c4fdf187ea8c04e6d3f64baf3db1ab)
- 5841108f038331d2c5179d16dcf9382c714deb3c942728306ed7929452939de2 (cfe5fb13da854f04aaa863931133281444eb5b7c)
- be0500bf56a7b681ed76563821bd46473d95cbe40d2f2e32cb107f62b88717af (995df642750e4012e4ca4ee3ea39893f886e4c42)
- 446494d508567dd134cd587a9258380f724f7ce6bac167c1ec0c323adc8e18ba (f3138b8932013dc963bd7c69f6fd07789660cb2b)
- 57bc6efdec9dd6ea5dd3033db90fd0204b52c0693ba252d437456d64d18c7a71 (afa137bfdaba70ec1483dd493b7c470e15481e90)
- 07b9b2b5da4bec44ada269188322f1d75ac911a49d5438a62081cea8c816f3c3 (a95361929fcdb6edbdb70e79f2c8d5c10a27c7f2)
- 88e3605b0a11a6a93aa05c534e6593f742c067124c32e7a30fc51ee5324164a3 (f8b4e97be7f6f41d8ebecd7b138aa322496625bd)
- 56ae3ee41046689e4671f601311fc1776bf126d943810a95e19bbd6652e6201d (4f7e1863396579b9a056c2b342dd6a556e477c2d)
- d8f18abda017231c5e2560ebacf84babbdabf2c9994d6bcffacc069e145e18c4 (65ffc682110e5a6c54a4cf780cac4c16bcd4009f)
- f9a946480b960f43da693aebe471c9a39d8dc4c3cd3121d10473fb7c9edc0113 (502f8ee49dee3bfa3708e6faf997ad5778468f81)
- 307b1db9791c12c5e7d4744161cae054fcc64de3a1a5d3ee8b8e1b79833c55ca (439be0a03e521a8b0414bf9b9b65f96659673e7c)
- f7b21c3b173c5e548cb0c472c8eeee823c0b007295dbbda8c91fe552f0f119ea (7853fcaa495dc80ae1aaef37ebdbb59cb4abe101)
- faec35a2af3f8febeb5675064093871c4baf6ec0c402f5a1c93bb52b0bba6b45 (199af139ef112a4204cefab0a3ffb978599ce891)
- ae20e4842a490bcfced81fbbd99c2cb22fba1da5ba83569ae8c1572e59da9ec1 (94941b83a462a9675813bca0b4ae4384f1c80358)
- 8e2b770024669585602e72b86b476092d04985b66293c7d85a2faef93e329045 (ceaa3f03a60741274f270f2e2d527808bec4e440)
- a1426ec4036a7a865efa93a6c74bde9a551fda7488d6078b1788d67a3e27663d (e3c88505dab2a57c29cd25064192418b54b0e9b4)
- 0aff965623058242ae9262e2b8d2a10b0eb8f36edc93a81322e7615689696dcf (9e15ecea112877b92481fc692dffd760504e2acb)
- 1f42badc004ffc7bf06ab75b419722a2210bb1c595c7ebf1f75b7fbaa7415bcf (76478604c4952dc7a025992dba4ee4552da314bd)
- 3f36e6f1c5bc83e512bd1ae43237deede4719b6a215f56a53619e1c7c2844938 (807321ec2530de16dad87664cb7ee6465888f5aa)
- ba989ee49b0c8742ee1784c7563272586fdad2dbea9dd5297ebc09b6ca059e20 (74b84d3da3a5ab3e784f1637445bf2c928b4c277)
- 2194761b943bbb6d1088be68f185855597aa690acf2c8819b19395a5b4f11282 (a9c201f746ed118424c7ae17a024429379d857f5)
- ab8eabf53e4a48998c706c815c76dd8d1c4a879ca5dcb00f033c16c3edcdb15a (1f95bbe70f6981c970d1484889fb6883bdd2d246)
- 11cf6190f6b1e40040eee98b31e997c84c57d4e78912788a7d8b51e99e0c9a6a (824059cf5f8bb4e25255d0abbdf0b6a2d8dfe910)
- b32dba3f6f8b8e0379aaa7a70b857fcd0310cf0fe7050e0b5b792782760bc510 (854992517bb78a2efee1dfefdf81a571b48acda5)

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,198 @@
+{
+  "_name_or_path": "/mnt/bn/vl-research-cn-boli01-hl/checkpoints/llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-72B-Instruct-mid_to_final_next_3m_am9_july13",
+  "architectures": [
+    "LlavaQwenForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "image_aspect_ratio": "anyres_max_9",
+  "image_crop_resolution": null,
+  "image_grid_pinpoints": [
+    [
+      384,
+      384
+    ],
+    [
+      384,
+      768
+    ],
+    [
+      384,
+      1152
+    ],
+    [
+      384,
+      1536
+    ],
+    [
+      384,
+      1920
+    ],
+    [
+      384,
+      2304
+    ],
+    [
+      768,
+      384
+    ],
+    [
+      768,
+      768
+    ],
+    [
+      768,
+      1152
+    ],
+    [
+      768,
+      1536
+    ],
+    [
+      768,
+      1920
+    ],
+    [
+      768,
+      2304
+    ],
+    [
+      1152,
+      384
+    ],
+    [
+      1152,
+      768
+    ],
+    [
+      1152,
+      1152
+    ],
+    [
+      1152,
+      1536
+    ],
+    [
+      1152,
+      1920
+    ],
+    [
+      1152,
+      2304
+    ],
+    [
+      1536,
+      384
+    ],
+    [
+      1536,
+      768
+    ],
+    [
+      1536,
+      1152
+    ],
+    [
+      1536,
+      1536
+    ],
+    [
+      1536,
+      1920
+    ],
+    [
+      1536,
+      2304
+    ],
+    [
+      1920,
+      384
+    ],
+    [
+      1920,
+      768
+    ],
+    [
+      1920,
+      1152
+    ],
+    [
+      1920,
+      1536
+    ],
+    [
+      1920,
+      1920
+    ],
+    [
+      1920,
+      2304
+    ],
+    [
+      2304,
+      384
+    ],
+    [
+      2304,
+      768
+    ],
+    [
+      2304,
+      1152
+    ],
+    [
+      2304,
+      1536
+    ],
+    [
+      2304,
+      1920
+    ],
+    [
+      2304,
+      2304
+    ]
+  ],
+  "image_split_resolution": null,
+  "image_token_index": 151646,
+  "initializer_range": 0.02,
+  "intermediate_size": 29568,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 80,
+  "mm_hidden_size": 1152,
+  "mm_patch_merge_type": "spatial_unpad",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_spatial_pool_mode": "bilinear",
+  "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "google/siglip-so400m-patch14-384",
+  "mm_vision_tower_lr": 2e-07,
+  "model_type": "llava",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pos_skipping_range": 4096,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 32768,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_pos_skipping": false,
+  "use_sliding_window": false,
+  "vision_tower_pretrained": null,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.40.0.dev0"
+}

model-00001-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00b71150f05b9f2121994b8b38ba446bbdac7e410693ca63531c98f065876b69
+size 4548815200

model-00002-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0461c729762e1ab8fa708121ff1094c793937b76b8c8af33ebba8c6a48ed676c
+size 4964101384

model-00003-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:727ff9c9e0b4329c1cc0fad9bfc6fa89d5b3fe1ed8cc1829aa3ecb99517e8ed3
+size 4781637328

model-00004-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbf13ac5a1077acda42a25d431672134b1ebefccd801a2af292cf1db6cb14344
+size 4781670320

model-00005-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdabde908a7afcab2bc1811334abff1e118e736fa0142a4551db5152344decfe
+size 4781670360

model-00006-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:477330e76ff49ec31a09185bfbe1f2e7f4cc7fddd02967b96e3db25da1577739
+size 4964101416

model-00007-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf7f7ea8a3b66cba6c80ee81bed66c6ef1132112e9a6eb6abfdf6d180256cebd
+size 4781637360

model-00008-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62062ddfbb4dacc87a237997bbb4e429d1eb3f7f1271120356855094cf36b7eb
+size 4781670360

model-00009-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fca8e6260170e4c9fbe9e665d8b85197addc14f26f56210fc070f471d89a886
+size 4781670360

model-00010-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e942d1ae16d564992d5103d95a7892a1dc1131f931e9bd834ace3182c451ede5
+size 4964101416

model-00011-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed035d3085f6b78fe19a6c8eeb8affbd5e471c9b4e01f81a0789e90c88aeb982
+size 4781637360

model-00012-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2812c16e1a17341cf1c71319c4269a77c11f09e745abd576db7cedae9fcaa14d
+size 4781670360

model-00013-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5a4b78d425a0c8559cac1db7561e7e61e22178da8c1cee4266c65c085d9704e
+size 4781670360

model-00014-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7226f2192859b6b52bbeeb3a4a2f89252b6949550d0ad9b4ce990aeb9aab1686
+size 4964101416

model-00015-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41407d08ce82667cea2a6fcdbc90dba8f13167a9059f679e3dae40bf8aa72483
+size 4781637360

model-00016-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6afafb2a8abe13388bfe2082996ab93a10f6329a2b493375f450695288348165
+size 4781670360

model-00017-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fce9f526c27f3530a9562c35d67ebfa33ca676f26ec41627608563ea9b3323e6
+size 4781670360

model-00018-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe33cdbf1fbaab5bdde3e3ece25cbb4a74b5df1091c705c40d00da1bef4f9936
+size 4964101416

model-00019-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8264c99127bc6fc27c1336f090049b9dc278c7032ae3aa372523751c7a9447c7
+size 4781637360

model-00020-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f78ac581b5b4f995bd38d12002c823a72cd94ab3a4e91696a27c756d7b2873c
+size 4781670360

model-00021-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31ca87bded1a518caf907469f7c10421f16686107554d2ad3fa27af7ac31511c
+size 4781670360

model-00022-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f840f9c2a8f375fb202fb1738e372f2c9eb6fb21bb279a325460cef866715e2
+size 4964101416

model-00023-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b48f98ca38730e9c3e8eab39666f85f41931493b57a73c1ee5c222d961e30a7f
+size 4781637360

model-00024-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17cc369abf6dfc32111e86a9f7af9d0bf8fcf78828558096cea79d0199e4b3c2
+size 4781670360

model-00025-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cde67eae526436c11d293ec007033aae4454cbab8188e0b4161a6f8791a90f9
+size 4781670360

model-00026-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7bd636d7b2f42e85578568e4f04a7be9c90e28a3f4c043075ccb3684d8ea273
+size 4964101416

model-00027-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:258993fef86216b20664755949ae6521e434d77288e777c113a6fd906cc70ed1
+size 4781637360

model-00028-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:230eb4385c9b6d5cdffeeeb10234c723db28a8588d8730042beff553a3bd79ff
+size 4781670360

model-00029-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0af44c56bf29214d286c8bc4c3d4f972d8626e035da653bbbb7ca7dab02ebf11
+size 4781670360

model-00030-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:164a86b327dbeaef043f1f19ee025d37880f0ca0b12d2e609734c7a0d024bec1
+size 4157433952

model-00031-of-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e1a8bb41773ead33f9f370193a06f2ce1525699b061c014036a93c3f7524aba
+size 2491416704

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,457 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 61,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.765191996253847,
+      "learning_rate": 2.5e-07,
+      "loss": 1.0461,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 4.0641282279063455,
+      "learning_rate": 5e-07,
+      "loss": 1.0458,
+      "step": 2
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 3.7765443388481783,
+      "learning_rate": 4.996456739191904e-07,
+      "loss": 1.0684,
+      "step": 3
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 3.4137815575539796,
+      "learning_rate": 4.985837000525343e-07,
+      "loss": 1.0314,
+      "step": 4
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.3692459406727107,
+      "learning_rate": 4.968170886803361e-07,
+      "loss": 1.0465,
+      "step": 5
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.41903215526812,
+      "learning_rate": 4.943508474544666e-07,
+      "loss": 0.9973,
+      "step": 6
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 3.5409185994032644,
+      "learning_rate": 4.91191967203629e-07,
+      "loss": 1.0003,
+      "step": 7
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 3.2875389190594584,
+      "learning_rate": 4.873494021170954e-07,
+      "loss": 1.0126,
+      "step": 8
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 3.1966679962173004,
+      "learning_rate": 4.828340443630846e-07,
+      "loss": 1.0149,
+      "step": 9
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.220278106251628,
+      "learning_rate": 4.776586932137283e-07,
+      "loss": 1.0149,
+      "step": 10
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 5.120652614407811,
+      "learning_rate": 4.7183801876414286e-07,
+      "loss": 1.0208,
+      "step": 11
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 3.428077957669144,
+      "learning_rate": 4.653885203484515e-07,
+      "loss": 1.0378,
+      "step": 12
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 3.7962383367663906,
+      "learning_rate": 4.583284797706287e-07,
+      "loss": 1.0135,
+      "step": 13
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 2.9907595309256267,
+      "learning_rate": 4.5067790948274085e-07,
+      "loss": 0.9998,
+      "step": 14
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 3.161110263982432,
+      "learning_rate": 4.4245849585747655e-07,
+      "loss": 1.0069,
+      "step": 15
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.886380477987417,
+      "learning_rate": 4.336935377157668e-07,
+      "loss": 0.9827,
+      "step": 16
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.376879009946129,
+      "learning_rate": 4.244078802837462e-07,
+      "loss": 0.9783,
+      "step": 17
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.6892749834464516,
+      "learning_rate": 4.146278447662597e-07,
+      "loss": 0.9585,
+      "step": 18
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 2.3786851686843105,
+      "learning_rate": 4.0438115373654795e-07,
+      "loss": 0.9677,
+      "step": 19
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 2.1590733636497754,
+      "learning_rate": 3.9369685255360173e-07,
+      "loss": 0.9472,
+      "step": 20
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.9865479320238961,
+      "learning_rate": 3.826052270299356e-07,
+      "loss": 0.9533,
+      "step": 21
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.0228147756455974,
+      "learning_rate": 3.7113771758316255e-07,
+      "loss": 0.9366,
+      "step": 22
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.9372326169891063,
+      "learning_rate": 3.593268301147139e-07,
+      "loss": 0.9316,
+      "step": 23
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.6478279831526508,
+      "learning_rate": 3.472060438683302e-07,
+      "loss": 0.9248,
+      "step": 24
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 2.1263539873072306,
+      "learning_rate": 3.348097165295075e-07,
+      "loss": 0.9232,
+      "step": 25
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.833864927411976,
+      "learning_rate": 3.2217298683490525e-07,
+      "loss": 0.9349,
+      "step": 26
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.821858101250319,
+      "learning_rate": 3.0933167496777873e-07,
+      "loss": 0.9038,
+      "step": 27
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.375067752782225,
+      "learning_rate": 2.9632218102177856e-07,
+      "loss": 0.9208,
+      "step": 28
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.6452545248116937,
+      "learning_rate": 2.8318138182093047e-07,
+      "loss": 0.9091,
+      "step": 29
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 1.641648446261072,
+      "learning_rate": 2.6994652638827075e-07,
+      "loss": 0.8863,
+      "step": 30
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.8514627902865017,
+      "learning_rate": 2.566551303594437e-07,
+      "loss": 0.9176,
+      "step": 31
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.6398219929819895,
+      "learning_rate": 2.433448696405563e-07,
+      "loss": 0.9132,
+      "step": 32
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 1.6191504043540148,
+      "learning_rate": 2.300534736117292e-07,
+      "loss": 0.9188,
+      "step": 33
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.6846506224257867,
+      "learning_rate": 2.168186181790695e-07,
+      "loss": 0.9207,
+      "step": 34
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 2.702325993164427,
+      "learning_rate": 2.0367781897822144e-07,
+      "loss": 0.917,
+      "step": 35
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 4.5333338294812044,
+      "learning_rate": 1.9066832503222128e-07,
+      "loss": 0.9267,
+      "step": 36
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.831113061882906,
+      "learning_rate": 1.7782701316509478e-07,
+      "loss": 0.9067,
+      "step": 37
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.6699336990379,
+      "learning_rate": 1.651902834704924e-07,
+      "loss": 0.92,
+      "step": 38
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.8690462677412756,
+      "learning_rate": 1.5279395613166985e-07,
+      "loss": 0.942,
+      "step": 39
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 1.9247744555110595,
+      "learning_rate": 1.4067316988528616e-07,
+      "loss": 0.9024,
+      "step": 40
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.453181146995208,
+      "learning_rate": 1.2886228241683748e-07,
+      "loss": 0.9064,
+      "step": 41
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 2.049559625310238,
+      "learning_rate": 1.173947729700644e-07,
+      "loss": 0.9271,
+      "step": 42
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.486378300397099,
+      "learning_rate": 1.0630314744639829e-07,
+      "loss": 0.9109,
+      "step": 43
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.1416606235277196,
+      "learning_rate": 9.561884626345204e-08,
+      "loss": 0.904,
+      "step": 44
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.6338101300074668,
+      "learning_rate": 8.537215523374037e-08,
+      "loss": 0.9148,
+      "step": 45
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 2.3037793287537545,
+      "learning_rate": 7.559211971625384e-08,
+      "loss": 0.8772,
+      "step": 46
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 1.788820498612225,
+      "learning_rate": 6.630646228423323e-08,
+      "loss": 0.9081,
+      "step": 47
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 2.313616876377129,
+      "learning_rate": 5.75415041425234e-08,
+      "loss": 0.93,
+      "step": 48
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.8442253511582427,
+      "learning_rate": 4.932209051725914e-08,
+      "loss": 0.9303,
+      "step": 49
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.797668108469576,
+      "learning_rate": 4.167152022937123e-08,
+      "loss": 0.9046,
+      "step": 50
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 2.0071094870512707,
+      "learning_rate": 3.461147965154845e-08,
+      "loss": 0.8853,
+      "step": 51
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.5091131315393522,
+      "learning_rate": 2.816198123585714e-08,
+      "loss": 0.893,
+      "step": 52
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 2.291025373137871,
+      "learning_rate": 2.234130678627169e-08,
+      "loss": 0.9102,
+      "step": 53
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.975139175162289,
+      "learning_rate": 1.7165955636915392e-08,
+      "loss": 0.9448,
+      "step": 54
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.9662365790545857,
+      "learning_rate": 1.265059788290468e-08,
+      "loss": 0.9126,
+      "step": 55
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 1.5860718910737048,
+      "learning_rate": 8.808032796371017e-09,
+      "loss": 0.9008,
+      "step": 56
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 5.824152576947844,
+      "learning_rate": 5.649152545533331e-09,
+      "loss": 0.9104,
+      "step": 57
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.8084725184982782,
+      "learning_rate": 3.1829113196638613e-09,
+      "loss": 0.9108,
+      "step": 58
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 2.4499467355310878,
+      "learning_rate": 1.4162999474657266e-09,
+      "loss": 0.9218,
+      "step": 59
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 1.7234130969562493,
+      "learning_rate": 3.5432608080951386e-10,
+      "loss": 0.913,
+      "step": 60
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.5468535844514548,
+      "learning_rate": 0.0,
+      "loss": 0.9164,
+      "step": 61
+    },
+    {
+      "epoch": 1.0,
+      "step": 61,
+      "total_flos": 57696792150016.0,
+      "train_loss": 0.9464570713824914,
+      "train_runtime": 1092.378,
+      "train_samples_per_second": 14.334,
+      "train_steps_per_second": 0.056
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 61,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "total_flos": 57696792150016.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ceab2d9e97a5fdd56677e40f3d5a857675f74b9cbaae3c92d2ff81d15ec4a7e
+size 7928