Training in progress, step 25, checkpoint

last-checkpoint/README.md

@@ -1,5 +1,5 @@
 ---
-base_model: NousResearch/CodeLlama-7b-hf
+base_model: unsloth/Qwen2.5-Coder-7B
 library_name: peft
 ---
 
@@ -199,4 +199,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 ### Framework versions
 
-- PEFT 0.13.2
+- PEFT 0.14.0

last-checkpoint/adapter_config.json

@@ -1,8 +1,10 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "NousResearch/CodeLlama-7b-hf",
+  "base_model_name_or_path": "unsloth/Qwen2.5-Coder-7B",
   "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": null,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -11,6 +13,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 64,
+  "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "k_proj",
-    "o_proj",
+    "gate_proj",
     "up_proj",
-    "q_proj",
-    "v_proj",
     "down_proj",
-    "gate_proj"
+    "o_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a16782ad6003cc249729eaf787b2f12c4580a66df7a4ad911042842ad8b37f3
-size 319876032
+oid sha256:0c8d32944e4454be4bdddf2e55f719383daf3c04aa97315c721bcb3c26a5548b
+size 323014168

last-checkpoint/added_tokens.json

@@ -1,13 +1,25 @@
 {
-  "<|assistant|>": 32001,
-  "<|endoftext|>": 32000,
-  "<|end|>": 32007,
-  "<|placeholder1|>": 32002,
-  "<|placeholder2|>": 32003,
-  "<|placeholder3|>": 32004,
-  "<|placeholder4|>": 32005,
-  "<|placeholder5|>": 32008,
-  "<|placeholder6|>": 32009,
-  "<|system|>": 32006,
-  "<|user|>": 32010
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|PAD_TOKEN|>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
 }

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07b7bb7ee1bd78fc86f3b3d334c0f723efc54a0e89cee8a3e6addb29cdc51e70
-size 640009682
+oid sha256:50fac20b8af7089797be365f66d5653744e9733a3a115f1d45df97adb16cbd02
+size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa6f173b1b026c367b70c1fce82f123265c6bc34d13a332bc2c892e213fccbb7
-size 15024
+oid sha256:3e3cfaa35ecb32c58a62906e3cd360d45beac47233854c9b1e0fc070e573e580
+size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc3583ab6d26a0a402902114950375996567c99dccbbc5e283def019711614f9
-size 15024
+oid sha256:a5d333ab5eb402c3ad15d011ab1cda0069a64cfa2aa10d382897e584855eb9e0
+size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
+oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
 size 1064

last-checkpoint/special_tokens_map.json

@@ -1,27 +1,28 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
   "eos_token": {
-    "content": "</s>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
+    "content": "<|PAD_TOKEN|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

last-checkpoint/tokenizer_config.json

@@ -1,26 +1,185 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "add_prefix_space": null,
+  "add_bos_token": false,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
+    "151643": {
+      "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<s>",
+    "151644": {
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -28,15 +187,31 @@
       "special": true
     }
   },
-  "bos_token": "<s>",
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
   "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "legacy": true,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
 }

last-checkpoint/trainer_state.json

@@ -1,392 +1,209 @@
 {
-  "best_metric": 4.127087231609039e-05,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 1.0496732026143791,
+  "best_metric": 1.957382082939148,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.016421709499958945,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.02091503267973856,
-      "grad_norm": 102.72461700439453,
+      "epoch": 0.0006568683799983579,
+      "grad_norm": 21.116296768188477,
       "learning_rate": 5e-05,
-      "loss": 148.2262,
+      "loss": 47.7589,
       "step": 1
     },
     {
-      "epoch": 0.02091503267973856,
-      "eval_loss": 9.406306266784668,
-      "eval_runtime": 26.0996,
-      "eval_samples_per_second": 3.103,
-      "eval_steps_per_second": 1.571,
+      "epoch": 0.0006568683799983579,
+      "eval_loss": 4.154504299163818,
+      "eval_runtime": 573.0772,
+      "eval_samples_per_second": 8.948,
+      "eval_steps_per_second": 2.237,
       "step": 1
     },
     {
-      "epoch": 0.04183006535947712,
-      "grad_norm": 90.18787384033203,
+      "epoch": 0.0013137367599967158,
+      "grad_norm": 18.675199508666992,
       "learning_rate": 0.0001,
-      "loss": 145.0047,
+      "loss": 53.2593,
       "step": 2
     },
     {
-      "epoch": 0.06274509803921569,
-      "grad_norm": 102.96981048583984,
+      "epoch": 0.0019706051399950735,
+      "grad_norm": 20.739986419677734,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 137.3407,
+      "loss": 51.8736,
       "step": 3
     },
     {
-      "epoch": 0.08366013071895424,
-      "grad_norm": 145.56475830078125,
+      "epoch": 0.0026274735199934315,
+      "grad_norm": 21.701404571533203,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 134.6917,
+      "loss": 56.3313,
       "step": 4
     },
     {
-      "epoch": 0.10457516339869281,
-      "grad_norm": 140.44082641601562,
+      "epoch": 0.003284341899991789,
+      "grad_norm": 21.279020309448242,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 118.558,
+      "loss": 50.3041,
       "step": 5
     },
     {
-      "epoch": 0.12549019607843137,
-      "grad_norm": 135.83241271972656,
+      "epoch": 0.003941210279990147,
+      "grad_norm": 19.682722091674805,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 101.6476,
+      "loss": 46.2417,
       "step": 6
     },
     {
-      "epoch": 0.14640522875816994,
-      "grad_norm": 116.04879760742188,
+      "epoch": 0.004598078659988505,
+      "grad_norm": 21.489429473876953,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 77.2923,
+      "loss": 44.0281,
       "step": 7
     },
     {
-      "epoch": 0.16732026143790849,
-      "grad_norm": 116.68311309814453,
+      "epoch": 0.005254947039986863,
+      "grad_norm": 23.246824264526367,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 60.8297,
+      "loss": 44.2746,
       "step": 8
     },
     {
-      "epoch": 0.18823529411764706,
-      "grad_norm": 101.5295639038086,
+      "epoch": 0.00591181541998522,
+      "grad_norm": 25.966197967529297,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 45.67,
+      "loss": 42.628,
       "step": 9
     },
     {
-      "epoch": 0.20915032679738563,
-      "grad_norm": 85.99949645996094,
+      "epoch": 0.006568683799983578,
+      "grad_norm": 29.68147850036621,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 38.6756,
+      "loss": 39.1083,
       "step": 10
     },
     {
-      "epoch": 0.23006535947712417,
-      "grad_norm": 64.54862213134766,
+      "epoch": 0.007225552179981936,
+      "grad_norm": 29.226259231567383,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 26.7462,
+      "loss": 37.2143,
       "step": 11
     },
     {
-      "epoch": 0.25098039215686274,
-      "grad_norm": 37.021934509277344,
+      "epoch": 0.007882420559980294,
+      "grad_norm": 29.88581657409668,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 11.3077,
+      "loss": 37.5903,
       "step": 12
     },
     {
-      "epoch": 0.2718954248366013,
-      "grad_norm": 33.68046569824219,
+      "epoch": 0.008539288939978651,
+      "grad_norm": 24.698503494262695,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 8.8502,
+      "loss": 38.8273,
       "step": 13
     },
     {
-      "epoch": 0.2928104575163399,
-      "grad_norm": 69.80364990234375,
+      "epoch": 0.00919615731997701,
+      "grad_norm": 22.38409423828125,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 11.204,
+      "loss": 39.2722,
       "step": 14
     },
     {
-      "epoch": 0.3137254901960784,
-      "grad_norm": 64.46556091308594,
+      "epoch": 0.009853025699975367,
+      "grad_norm": 17.25520133972168,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 8.0732,
+      "loss": 37.6769,
       "step": 15
     },
     {
-      "epoch": 0.33464052287581697,
-      "grad_norm": 22.950719833374023,
+      "epoch": 0.010509894079973726,
+      "grad_norm": 15.956023216247559,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 2.3239,
+      "loss": 34.8531,
       "step": 16
     },
     {
-      "epoch": 0.35555555555555557,
-      "grad_norm": 27.570941925048828,
+      "epoch": 0.011166762459972083,
+      "grad_norm": 18.063295364379883,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 3.8739,
+      "loss": 36.7135,
       "step": 17
     },
     {
-      "epoch": 0.3764705882352941,
-      "grad_norm": 52.724632263183594,
+      "epoch": 0.01182363083997044,
+      "grad_norm": 18.19580841064453,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 2.7403,
+      "loss": 36.0943,
       "step": 18
     },
     {
-      "epoch": 0.39738562091503266,
-      "grad_norm": 33.629058837890625,
+      "epoch": 0.0124804992199688,
+      "grad_norm": 19.19350242614746,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 1.5774,
+      "loss": 34.9283,
       "step": 19
     },
     {
-      "epoch": 0.41830065359477125,
-      "grad_norm": 10.682621002197266,
+      "epoch": 0.013137367599967156,
+      "grad_norm": 15.737515449523926,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 0.6792,
+      "loss": 35.9358,
       "step": 20
     },
     {
-      "epoch": 0.4392156862745098,
-      "grad_norm": 6.780605792999268,
+      "epoch": 0.013794235979965515,
+      "grad_norm": 17.68427276611328,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 0.2117,
+      "loss": 35.4988,
       "step": 21
     },
     {
-      "epoch": 0.46013071895424834,
-      "grad_norm": 22.594688415527344,
+      "epoch": 0.014451104359963872,
+      "grad_norm": 15.05672550201416,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 0.998,
+      "loss": 34.0991,
       "step": 22
     },
     {
-      "epoch": 0.48104575163398694,
-      "grad_norm": 6.626839637756348,
+      "epoch": 0.01510797273996223,
+      "grad_norm": 15.203287124633789,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 0.3769,
+      "loss": 35.6672,
       "step": 23
     },
     {
-      "epoch": 0.5019607843137255,
-      "grad_norm": 1.138240933418274,
+      "epoch": 0.015764841119960588,
+      "grad_norm": 15.746703147888184,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 0.0633,
+      "loss": 35.0715,
       "step": 24
     },
     {
-      "epoch": 0.5228758169934641,
-      "grad_norm": 1.8117948770523071,
+      "epoch": 0.016421709499958945,
+      "grad_norm": 16.753942489624023,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 0.0665,
+      "loss": 35.2284,
       "step": 25
     },
     {
-      "epoch": 0.5228758169934641,
-      "eval_loss": 0.00532330758869648,
-      "eval_runtime": 26.0795,
-      "eval_samples_per_second": 3.106,
-      "eval_steps_per_second": 1.572,
+      "epoch": 0.016421709499958945,
+      "eval_loss": 1.957382082939148,
+      "eval_runtime": 575.1539,
+      "eval_samples_per_second": 8.916,
+      "eval_steps_per_second": 2.229,
       "step": 25
-    },
-    {
-      "epoch": 0.5437908496732026,
-      "grad_norm": 8.163567543029785,
-      "learning_rate": 5e-05,
-      "loss": 0.172,
-      "step": 26
-    },
-    {
-      "epoch": 0.5647058823529412,
-      "grad_norm": 2.176654577255249,
-      "learning_rate": 4.6729843538492847e-05,
-      "loss": 0.0438,
-      "step": 27
-    },
-    {
-      "epoch": 0.5856209150326798,
-      "grad_norm": 0.09583692997694016,
-      "learning_rate": 4.347369038899744e-05,
-      "loss": 0.0033,
-      "step": 28
-    },
-    {
-      "epoch": 0.6065359477124183,
-      "grad_norm": 2.4841692447662354,
-      "learning_rate": 4.0245483899193595e-05,
-      "loss": 0.0293,
-      "step": 29
-    },
-    {
-      "epoch": 0.6274509803921569,
-      "grad_norm": 0.9432563185691833,
-      "learning_rate": 3.705904774487396e-05,
-      "loss": 0.0176,
-      "step": 30
-    },
-    {
-      "epoch": 0.6483660130718955,
-      "grad_norm": 0.29981163144111633,
-      "learning_rate": 3.392802673484193e-05,
-      "loss": 0.0095,
-      "step": 31
-    },
-    {
-      "epoch": 0.6692810457516339,
-      "grad_norm": 0.13397172093391418,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 0.0034,
-      "step": 32
-    },
-    {
-      "epoch": 0.6901960784313725,
-      "grad_norm": 0.26384004950523376,
-      "learning_rate": 2.7885565489049946e-05,
-      "loss": 0.0036,
-      "step": 33
-    },
-    {
-      "epoch": 0.7111111111111111,
-      "grad_norm": 0.017268378287553787,
-      "learning_rate": 2.500000000000001e-05,
-      "loss": 0.0007,
-      "step": 34
-    },
-    {
-      "epoch": 0.7320261437908496,
-      "grad_norm": 0.0771813616156578,
-      "learning_rate": 2.2221488349019903e-05,
-      "loss": 0.0022,
-      "step": 35
-    },
-    {
-      "epoch": 0.7529411764705882,
-      "grad_norm": 0.06307241320610046,
-      "learning_rate": 1.9561928549563968e-05,
-      "loss": 0.0011,
-      "step": 36
-    },
-    {
-      "epoch": 0.7738562091503268,
-      "grad_norm": 0.009056968614459038,
-      "learning_rate": 1.703270924499656e-05,
-      "loss": 0.0003,
-      "step": 37
-    },
-    {
-      "epoch": 0.7947712418300653,
-      "grad_norm": 0.02682294324040413,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.0008,
-      "step": 38
-    },
-    {
-      "epoch": 0.8156862745098039,
-      "grad_norm": 0.03674069046974182,
-      "learning_rate": 1.2408009626051137e-05,
-      "loss": 0.0013,
-      "step": 39
-    },
-    {
-      "epoch": 0.8366013071895425,
-      "grad_norm": 0.011068358086049557,
-      "learning_rate": 1.0332332985438248e-05,
-      "loss": 0.0005,
-      "step": 40
-    },
-    {
-      "epoch": 0.857516339869281,
-      "grad_norm": 0.013999490067362785,
-      "learning_rate": 8.426519384872733e-06,
-      "loss": 0.0007,
-      "step": 41
-    },
-    {
-      "epoch": 0.8784313725490196,
-      "grad_norm": 0.011875639669597149,
-      "learning_rate": 6.698729810778065e-06,
-      "loss": 0.0006,
-      "step": 42
-    },
-    {
-      "epoch": 0.8993464052287582,
-      "grad_norm": 0.12404092401266098,
-      "learning_rate": 5.156362923365588e-06,
-      "loss": 0.0015,
-      "step": 43
-    },
-    {
-      "epoch": 0.9202614379084967,
-      "grad_norm": 0.03556958585977554,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.001,
-      "step": 44
-    },
-    {
-      "epoch": 0.9411764705882353,
-      "grad_norm": 6.352353096008301,
-      "learning_rate": 2.653493525244721e-06,
-      "loss": 0.0426,
-      "step": 45
-    },
-    {
-      "epoch": 0.9620915032679739,
-      "grad_norm": 0.0167868509888649,
-      "learning_rate": 1.70370868554659e-06,
-      "loss": 0.0007,
-      "step": 46
-    },
-    {
-      "epoch": 0.9830065359477124,
-      "grad_norm": 0.024576369673013687,
-      "learning_rate": 9.607359798384785e-07,
-      "loss": 0.0005,
-      "step": 47
-    },
-    {
-      "epoch": 1.007843137254902,
-      "grad_norm": 0.009638285264372826,
-      "learning_rate": 4.277569313094809e-07,
-      "loss": 0.0005,
-      "step": 48
-    },
-    {
-      "epoch": 1.0287581699346404,
-      "grad_norm": 0.007980446331202984,
-      "learning_rate": 1.0705383806982606e-07,
-      "loss": 0.0004,
-      "step": 49
-    },
-    {
-      "epoch": 1.0496732026143791,
-      "grad_norm": 0.006425910629332066,
-      "learning_rate": 0.0,
-      "loss": 0.0003,
-      "step": 50
-    },
-    {
-      "epoch": 1.0496732026143791,
-      "eval_loss": 4.127087231609039e-05,
-      "eval_runtime": 26.0704,
-      "eval_samples_per_second": 3.107,
-      "eval_steps_per_second": 1.573,
-      "step": 50
     }
   ],
   "logging_steps": 1,
   "max_steps": 50,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 1,
   "save_steps": 25,
   "stateful_callbacks": {
     "EarlyStoppingCallback": {
@@ -404,12 +221,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.314789078859776e+17,
+  "total_flos": 1.406014452662272e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10fa75858312944c66542aee6d6a3e31ea121a457c0727d1a86e3c74f020b648
-size 6776
+oid sha256:bac41a9514476834778779d021c3d120cffc738ddcbe07213824d214167aadd3
+size 6904