Training in progress, step 400, checkpoint

.gitattributes

@@ -48,3 +48,8 @@ checkpoint-300/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
 checkpoint-300/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
 checkpoint-300/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
 checkpoint-300/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-400/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
+checkpoint-400/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-400/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-400/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-400/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text

checkpoint-400/optimizer_0/.metadata

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a74ba8fcf2d857e573ced9e8ccd472ece612ef1ca47c4379e8bbc05bf43f4fa8
+size 2108254

checkpoint-400/optimizer_0/__0_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97526ddea90efa3d0ae7a7d8514c3026bb492dcb26c1a21808ad1abe933f1b3e
+size 13256787644

checkpoint-400/optimizer_0/__1_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1dc15f1fbdfe70cae527d0d50c5cbc873ad34a6bfd62cc2ba9cdbfbb83b449c
+size 13257964260

checkpoint-400/pytorch_model_fsdp_0/__0_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3269587842cb193ba57dc01027f127072026f88cb973af7a4b41959bb536545
+size 6628321920

checkpoint-400/pytorch_model_fsdp_0/__1_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a99872f16f3c83f33eccb1cd9309dc05ab2df6d7468d08a343ee4befa4c9bde5
+size 6628321920

checkpoint-400/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db5d99a6c1f613178aee8a88858e35c43888794b32c3c9357e466f03e1f5906e
+size 14512

checkpoint-400/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29747cb7712d7e98c4ad5d236c3fc140ebea524534e69095c72c88ed3ebc8530
+size 14512

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7febe3a2ca1c0d459643964286e56b56721c9bc05dbbeb61e176c534c63819d8
+size 1000

checkpoint-400/trainer_state.json

@@ -0,0 +1,385 @@
+{
+  "best_metric": 0.4464975595474243,
+  "best_model_checkpoint": "./llama3/30-08-24-Weni-Pipeline_test_Experiment with SFT and Llama3 70b-2_max_steps-1362_batch_8_2024-08-30/checkpoint-400",
+  "epoch": 1.76017601760176,
+  "eval_steps": 100,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04400440044004401,
+      "grad_norm": 0.5568628907203674,
+      "learning_rate": 7.5e-05,
+      "loss": 2.0875,
+      "step": 10
+    },
+    {
+      "epoch": 0.08800880088008801,
+      "grad_norm": 0.2537558972835541,
+      "learning_rate": 0.00015,
+      "loss": 0.9378,
+      "step": 20
+    },
+    {
+      "epoch": 0.132013201320132,
+      "grad_norm": 0.24558919668197632,
+      "learning_rate": 0.000225,
+      "loss": 0.7,
+      "step": 30
+    },
+    {
+      "epoch": 0.17601760176017603,
+      "grad_norm": 0.13937097787857056,
+      "learning_rate": 0.0003,
+      "loss": 0.6298,
+      "step": 40
+    },
+    {
+      "epoch": 0.22002200220022003,
+      "grad_norm": 0.1871194988489151,
+      "learning_rate": 0.00029995764763563235,
+      "loss": 0.6321,
+      "step": 50
+    },
+    {
+      "epoch": 0.264026402640264,
+      "grad_norm": 0.14626263082027435,
+      "learning_rate": 0.00029983061445883305,
+      "loss": 0.6403,
+      "step": 60
+    },
+    {
+      "epoch": 0.30803080308030806,
+      "grad_norm": 0.12049665302038193,
+      "learning_rate": 0.0002996189722050073,
+      "loss": 0.5998,
+      "step": 70
+    },
+    {
+      "epoch": 0.35203520352035206,
+      "grad_norm": 0.13617923855781555,
+      "learning_rate": 0.0002993228403881531,
+      "loss": 0.5942,
+      "step": 80
+    },
+    {
+      "epoch": 0.39603960396039606,
+      "grad_norm": 0.1271793246269226,
+      "learning_rate": 0.00029894238623337174,
+      "loss": 0.5647,
+      "step": 90
+    },
+    {
+      "epoch": 0.44004400440044006,
+      "grad_norm": 0.18757876753807068,
+      "learning_rate": 0.00029847782458243663,
+      "loss": 0.5619,
+      "step": 100
+    },
+    {
+      "epoch": 0.44004400440044006,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_f1_macro": 1.0,
+      "eval_f1_micro": 1.0,
+      "eval_loss": 0.5742923021316528,
+      "eval_precision": 1.0,
+      "eval_precision_macro": 1.0,
+      "eval_precision_micro": 1.0,
+      "eval_recall": 1.0,
+      "eval_recall_macro": 1.0,
+      "eval_recall_micro": 1.0,
+      "eval_runtime": 90.5857,
+      "eval_samples_per_second": 4.46,
+      "eval_steps_per_second": 1.115,
+      "step": 100
+    },
+    {
+      "epoch": 0.48404840484048406,
+      "grad_norm": 0.14132679998874664,
+      "learning_rate": 0.00029792941777247184,
+      "loss": 0.5584,
+      "step": 110
+    },
+    {
+      "epoch": 0.528052805280528,
+      "grad_norm": 0.15474887192249298,
+      "learning_rate": 0.0002972974754878111,
+      "loss": 0.5752,
+      "step": 120
+    },
+    {
+      "epoch": 0.5720572057205721,
+      "grad_norm": 0.13014496862888336,
+      "learning_rate": 0.0002965823545851199,
+      "loss": 0.5565,
+      "step": 130
+    },
+    {
+      "epoch": 0.6160616061606161,
+      "grad_norm": 0.12456662207841873,
+      "learning_rate": 0.00029578445889187865,
+      "loss": 0.5722,
+      "step": 140
+    },
+    {
+      "epoch": 0.6600660066006601,
+      "grad_norm": 0.12824317812919617,
+      "learning_rate": 0.00029490423897834234,
+      "loss": 0.523,
+      "step": 150
+    },
+    {
+      "epoch": 0.7040704070407041,
+      "grad_norm": 0.14279119670391083,
+      "learning_rate": 0.0002939421919031044,
+      "loss": 0.5523,
+      "step": 160
+    },
+    {
+      "epoch": 0.7480748074807481,
+      "grad_norm": 0.11781885474920273,
+      "learning_rate": 0.00029289886093240847,
+      "loss": 0.5291,
+      "step": 170
+    },
+    {
+      "epoch": 0.7920792079207921,
+      "grad_norm": 0.1608349233865738,
+      "learning_rate": 0.0002917748352333667,
+      "loss": 0.5417,
+      "step": 180
+    },
+    {
+      "epoch": 0.8360836083608361,
+      "grad_norm": 0.13777320086956024,
+      "learning_rate": 0.0002905707495412589,
+      "loss": 0.4967,
+      "step": 190
+    },
+    {
+      "epoch": 0.8800880088008801,
+      "grad_norm": 0.21577192842960358,
+      "learning_rate": 0.00028928728380109764,
+      "loss": 0.6545,
+      "step": 200
+    },
+    {
+      "epoch": 0.8800880088008801,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_f1_macro": 1.0,
+      "eval_f1_micro": 1.0,
+      "eval_loss": 0.6772989630699158,
+      "eval_precision": 1.0,
+      "eval_precision_macro": 1.0,
+      "eval_precision_micro": 1.0,
+      "eval_recall": 1.0,
+      "eval_recall_macro": 1.0,
+      "eval_recall_micro": 1.0,
+      "eval_runtime": 90.2067,
+      "eval_samples_per_second": 4.479,
+      "eval_steps_per_second": 1.12,
+      "step": 200
+    },
+    {
+      "epoch": 0.9240924092409241,
+      "grad_norm": 3.4556286334991455,
+      "learning_rate": 0.00028792516278366547,
+      "loss": 2.5144,
+      "step": 210
+    },
+    {
+      "epoch": 0.9680968096809681,
+      "grad_norm": 0.13046959042549133,
+      "learning_rate": 0.00028648515567623764,
+      "loss": 0.6004,
+      "step": 220
+    },
+    {
+      "epoch": 1.012101210121012,
+      "grad_norm": 0.39528125524520874,
+      "learning_rate": 0.0002849680756482235,
+      "loss": 0.5174,
+      "step": 230
+    },
+    {
+      "epoch": 1.056105610561056,
+      "grad_norm": 0.23764920234680176,
+      "learning_rate": 0.00028337477939197135,
+      "loss": 0.4065,
+      "step": 240
+    },
+    {
+      "epoch": 1.1001100110011002,
+      "grad_norm": 0.14821326732635498,
+      "learning_rate": 0.0002817061666389958,
+      "loss": 0.4425,
+      "step": 250
+    },
+    {
+      "epoch": 1.1441144114411441,
+      "grad_norm": 0.15903742611408234,
+      "learning_rate": 0.0002799631796519007,
+      "loss": 0.4107,
+      "step": 260
+    },
+    {
+      "epoch": 1.188118811881188,
+      "grad_norm": 0.16189326345920563,
+      "learning_rate": 0.00027814680269228574,
+      "loss": 0.4215,
+      "step": 270
+    },
+    {
+      "epoch": 1.2321232123212322,
+      "grad_norm": 0.20622508227825165,
+      "learning_rate": 0.00027625806146493523,
+      "loss": 0.3968,
+      "step": 280
+    },
+    {
+      "epoch": 1.2761276127612762,
+      "grad_norm": 0.17622467875480652,
+      "learning_rate": 0.0002742980225386045,
+      "loss": 0.4419,
+      "step": 290
+    },
+    {
+      "epoch": 1.3201320132013201,
+      "grad_norm": 0.12472284585237503,
+      "learning_rate": 0.0002722677927437307,
+      "loss": 0.396,
+      "step": 300
+    },
+    {
+      "epoch": 1.3201320132013201,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_f1_macro": 1.0,
+      "eval_f1_micro": 1.0,
+      "eval_loss": 0.5126128792762756,
+      "eval_precision": 1.0,
+      "eval_precision_macro": 1.0,
+      "eval_precision_micro": 1.0,
+      "eval_recall": 1.0,
+      "eval_recall_macro": 1.0,
+      "eval_recall_micro": 1.0,
+      "eval_runtime": 90.5135,
+      "eval_samples_per_second": 4.463,
+      "eval_steps_per_second": 1.116,
+      "step": 300
+    },
+    {
+      "epoch": 1.364136413641364,
+      "grad_norm": 0.17043285071849823,
+      "learning_rate": 0.0002701685185474076,
+      "loss": 0.4297,
+      "step": 310
+    },
+    {
+      "epoch": 1.408140814081408,
+      "grad_norm": 0.12771165370941162,
+      "learning_rate": 0.00026800138540597723,
+      "loss": 0.4174,
+      "step": 320
+    },
+    {
+      "epoch": 1.4521452145214522,
+      "grad_norm": 0.18149854242801666,
+      "learning_rate": 0.00026576761709560555,
+      "loss": 0.4313,
+      "step": 330
+    },
+    {
+      "epoch": 1.4961496149614961,
+      "grad_norm": 0.17737938463687897,
+      "learning_rate": 0.00026346847502121783,
+      "loss": 0.3693,
+      "step": 340
+    },
+    {
+      "epoch": 1.5401540154015403,
+      "grad_norm": 1.699652910232544,
+      "learning_rate": 0.0002611052575041856,
+      "loss": 0.4237,
+      "step": 350
+    },
+    {
+      "epoch": 1.5841584158415842,
+      "grad_norm": 0.18545816838741302,
+      "learning_rate": 0.00025867929904916704,
+      "loss": 0.3925,
+      "step": 360
+    },
+    {
+      "epoch": 1.6281628162816282,
+      "grad_norm": 0.16388830542564392,
+      "learning_rate": 0.0002561919695905145,
+      "loss": 0.3759,
+      "step": 370
+    },
+    {
+      "epoch": 1.6721672167216721,
+      "grad_norm": 0.1380474716424942,
+      "learning_rate": 0.0002536446737186751,
+      "loss": 0.3859,
+      "step": 380
+    },
+    {
+      "epoch": 1.716171617161716,
+      "grad_norm": 0.16071344912052155,
+      "learning_rate": 0.0002510388498870211,
+      "loss": 0.41,
+      "step": 390
+    },
+    {
+      "epoch": 1.76017601760176,
+      "grad_norm": 0.15108689665794373,
+      "learning_rate": 0.00024837596959955777,
+      "loss": 0.3645,
+      "step": 400
+    },
+    {
+      "epoch": 1.76017601760176,
+      "eval_accuracy": 1.0,
+      "eval_f1": 1.0,
+      "eval_f1_macro": 1.0,
+      "eval_f1_micro": 1.0,
+      "eval_loss": 0.4464975595474243,
+      "eval_precision": 1.0,
+      "eval_precision_macro": 1.0,
+      "eval_precision_micro": 1.0,
+      "eval_recall": 1.0,
+      "eval_recall_macro": 1.0,
+      "eval_recall_micro": 1.0,
+      "eval_runtime": 90.5484,
+      "eval_samples_per_second": 4.462,
+      "eval_steps_per_second": 1.115,
+      "step": 400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1362,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.589901503407063e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}