Training in progress, step 700

last-checkpoint/config.json

@@ -2,13 +2,9 @@
   "architectures": [
     "ModernLLMForCausalLM"
   ],
-  "auto_map": {
-    "AutoConfig": "configuration_modern_llm.ModernLLMConfig",
-    "AutoModelForCausalLM": "modeling_modern_llm.ModernLLMForCausalLM"
-  },
-  "bos_token_id": 151643,
+  "bos_token_id": 1,
   "dtype": "float32",
-  "eos_token_id": 151643,
+  "eos_token_id": 2,
   "hidden_size": 768,
   "intermediate_size": 2048,
   "max_position_embeddings": 2048,
@@ -16,7 +12,7 @@
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "num_key_value_heads": 4,
-  "pad_token_id": 151643,
+  "pad_token_id": 0,
   "rms_norm_eps": 1e-06,
   "rope_theta": 1000000.0,
   "transformers_version": "5.15.1",

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9efc1d1ce087b1564966c8d653dce7fda6eab490a18f4c3932091b6b26903a9e
+oid sha256:224bbc547320cbc7a57a274bef9f525f2e4be737031df14b601959f9380cb929
 size 1235573136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1139eebcc6feb15f65389c6aa09e1c5a7d2e3cf7d108e61d1f835820ec74c37
+oid sha256:f014f1f8cf2eb9a4ff44ad059ad7d7ab8356457d91805882d791c32ab849f992
 size 2471218763

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:711796bafdc96291445baaa7500e0225de597273f70515e4b639ff3ce6d4e57c
+oid sha256:68b03f74e10591ff22477365642275703166a34b306471da2a9df3e87497356f
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28f9eb0c69e2570740da7219ce2550d9ec1f1cae9401a3fd6e61ae4b99913ab1
+oid sha256:0471ce3745a36e49a3e0d19eac020ddc42dff8b92447d06fa38e6a682e228b19
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012,
+  "epoch": 0.01,
   "eval_steps": 500,
-  "global_step": 600,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -358,76 +358,6 @@
       "learning_rate": 0.0002976012024048096,
       "loss": 78.9918212890625,
       "step": 500
-    },
-    {
-      "epoch": 0.0102,
-      "grad_norm": 15.467362403869629,
-      "learning_rate": 0.00029754108216432863,
-      "loss": 124.401513671875,
-      "step": 510
-    },
-    {
-      "epoch": 0.0104,
-      "grad_norm": 13.991318702697754,
-      "learning_rate": 0.0002974809619238477,
-      "loss": 110.567431640625,
-      "step": 520
-    },
-    {
-      "epoch": 0.0106,
-      "grad_norm": 17.036069869995117,
-      "learning_rate": 0.0002974208416833667,
-      "loss": 104.7319580078125,
-      "step": 530
-    },
-    {
-      "epoch": 0.0108,
-      "grad_norm": 13.922304153442383,
-      "learning_rate": 0.0002973607214428857,
-      "loss": 100.63988647460937,
-      "step": 540
-    },
-    {
-      "epoch": 0.011,
-      "grad_norm": 13.223531723022461,
-      "learning_rate": 0.0002973006012024048,
-      "loss": 99.96443481445313,
-      "step": 550
-    },
-    {
-      "epoch": 0.0112,
-      "grad_norm": 14.53707504272461,
-      "learning_rate": 0.0002972404809619238,
-      "loss": 95.74251098632813,
-      "step": 560
-    },
-    {
-      "epoch": 0.0114,
-      "grad_norm": 14.91770076751709,
-      "learning_rate": 0.00029718036072144287,
-      "loss": 94.661767578125,
-      "step": 570
-    },
-    {
-      "epoch": 0.0116,
-      "grad_norm": 13.45614242553711,
-      "learning_rate": 0.0002971202404809619,
-      "loss": 90.941796875,
-      "step": 580
-    },
-    {
-      "epoch": 0.0118,
-      "grad_norm": 13.695131301879883,
-      "learning_rate": 0.00029706012024048096,
-      "loss": 92.9096923828125,
-      "step": 590
-    },
-    {
-      "epoch": 0.012,
-      "grad_norm": 16.406902313232422,
-      "learning_rate": 0.00029699999999999996,
-      "loss": 90.14566650390626,
-      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -447,7 +377,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9827296015518720.0,
+  "total_flos": 8161860202859520.0,
   "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:cba5aee8ada95f513ddc2ee5204de606b5a10fa33758d2e9c8bcbc512ffe2d6b
+oid sha256:3ead25e90961f39a7cf235a53c52302322d446327bb423dad890f04c47276211
 size 5201

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9efc1d1ce087b1564966c8d653dce7fda6eab490a18f4c3932091b6b26903a9e
+oid sha256:58886de0a0264c68415f0973d23f1c25b70abbb55d1ed2f9efc5c3bf293fcdc2
 size 1235573136