Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dedf215e9b506136c4eafaa5ca983fab54ed4eb2af03d61c3f95ec65d05da787
+oid sha256:82a943209b657b15ff00004efcaa88da19c9f1fd4603f11587c023fc47eda605
 size 579824888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa05fea595e28a91c765e7e95378a3f84bc9106fc2e6146f83186626bae9e711
+oid sha256:13ae1bff671c06244b8db21ff756e241dc09da71f9f9dc4f2ec99c071e13b99f
 size 1159794763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e06dfbf969388fb27efc692631d298abe0d1c57738a0c64598fe664b1ac46b1
+oid sha256:15bd918144b9671ae295d46e463180bdad2e73e51a7670636feb8fc58e14c426
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77f6f8dca22790e21b49d4a3e5b2c2d34a14c2511eb61bf406f69b9611e05181
+oid sha256:2666cc7db576490d8041b6acfda665e20af01ea5f7120fdf1d1c04b59674d0ca
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08,
+  "epoch": 0.12,
   "eval_steps": 1000,
-  "global_step": 4000,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -324,6 +324,164 @@
       "eval_samples_per_second": 307.255,
       "eval_steps_per_second": 19.312,
       "step": 4000
+    },
+    {
+      "epoch": 0.082,
+      "grad_norm": 0.20376908779144287,
+      "learning_rate": 0.000984595734445656,
+      "loss": 3.8685012817382813,
+      "step": 4100
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 0.18422065675258636,
+      "learning_rate": 0.0009838099869394353,
+      "loss": 3.853851318359375,
+      "step": 4200
+    },
+    {
+      "epoch": 0.086,
+      "grad_norm": 0.19115814566612244,
+      "learning_rate": 0.0009830050243260172,
+      "loss": 3.8678164672851563,
+      "step": 4300
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.20425236225128174,
+      "learning_rate": 0.0009821808785754791,
+      "loss": 3.8287237548828124,
+      "step": 4400
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.1944635510444641,
+      "learning_rate": 0.0009813375824197811,
+      "loss": 3.8451242065429687,
+      "step": 4500
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 0.17947296798229218,
+      "learning_rate": 0.0009804751693514645,
+      "loss": 3.845400695800781,
+      "step": 4600
+    },
+    {
+      "epoch": 0.094,
+      "grad_norm": 0.20076608657836914,
+      "learning_rate": 0.0009795936736223222,
+      "loss": 3.8257626342773436,
+      "step": 4700
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.18554596602916718,
+      "learning_rate": 0.0009786931302420386,
+      "loss": 3.808670959472656,
+      "step": 4800
+    },
+    {
+      "epoch": 0.098,
+      "grad_norm": 0.23913995921611786,
+      "learning_rate": 0.000977773574976799,
+      "loss": 3.810527038574219,
+      "step": 4900
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.18414103984832764,
+      "learning_rate": 0.0009768350443478686,
+      "loss": 3.7990948486328127,
+      "step": 5000
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.33500293894949945,
+      "eval_loss": 3.7702300548553467,
+      "eval_runtime": 6.4137,
+      "eval_samples_per_second": 302.634,
+      "eval_steps_per_second": 19.022,
+      "step": 5000
+    },
+    {
+      "epoch": 0.102,
+      "grad_norm": 0.20944379270076752,
+      "learning_rate": 0.0009758775756301432,
+      "loss": 3.798116455078125,
+      "step": 5100
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.18056762218475342,
+      "learning_rate": 0.0009749012068506673,
+      "loss": 3.7997445678710937,
+      "step": 5200
+    },
+    {
+      "epoch": 0.106,
+      "grad_norm": 0.20922255516052246,
+      "learning_rate": 0.000973905976787125,
+      "loss": 3.7765731811523438,
+      "step": 5300
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 0.19328580796718597,
+      "learning_rate": 0.0009728919249662993,
+      "loss": 3.729337463378906,
+      "step": 5400
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.2031419277191162,
+      "learning_rate": 0.0009718590916625022,
+      "loss": 3.744057922363281,
+      "step": 5500
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.19743800163269043,
+      "learning_rate": 0.0009708075178959756,
+      "loss": 3.7054071044921875,
+      "step": 5600
+    },
+    {
+      "epoch": 0.114,
+      "grad_norm": 0.1741236299276352,
+      "learning_rate": 0.0009697372454312618,
+      "loss": 3.699843444824219,
+      "step": 5700
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 0.1799750030040741,
+      "learning_rate": 0.0009686483167755448,
+      "loss": 3.7227572631835937,
+      "step": 5800
+    },
+    {
+      "epoch": 0.118,
+      "grad_norm": 0.2036087065935135,
+      "learning_rate": 0.000967540775176962,
+      "loss": 3.6742709350585936,
+      "step": 5900
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.21463191509246826,
+      "learning_rate": 0.0009664146646228871,
+      "loss": 3.6995980834960935,
+      "step": 6000
+    },
+    {
+      "epoch": 0.12,
+      "eval_accuracy": 0.34141821705074654,
+      "eval_loss": 3.711214303970337,
+      "eval_runtime": 6.3349,
+      "eval_samples_per_second": 306.4,
+      "eval_steps_per_second": 19.259,
+      "step": 6000
     }
   ],
   "logging_steps": 100,
@@ -343,7 +501,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5679843467264e+17,
+  "total_flos": 2.3519765200896e+17,
   "train_batch_size": 120,
   "trial_name": null,
   "trial_params": null