Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b12795eb294f14f19216ce7303683953962bfbde3b70ee33eccae088736dd2f
+oid sha256:93b4d618fee0aaf987ff44511c965a4a13d55a3d93f354ed73c1f91c3e21dccc
 size 496262784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a40275d08a6ee771906da7744e5ecf4905eb675617a98a372c4b33530e6da83d
+oid sha256:d79704be2307835f0582a7f7abe29d698ca7dbc76fdb78dc7bbfd0aaa6990b77
 size 992621963

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5364569e6210839a1caff47d9b08a64d50dda76f4704960ecdead9f41b7df112
+oid sha256:c9e2628e78d1dc996f476f66725a5d868b6e07dce08fc0df5d5fb50fcc8f9636
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a39530bbcd5c6be69add23d3653760d20540490f7a104a2dfa0a07555ccf4486
+oid sha256:c683ea10141469aa50dfa283ef5ec8ac410a06cef28bfb1e66e6a7d94e82730d
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04,
+  "epoch": 0.08,
   "eval_steps": 1000,
-  "global_step": 2000,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -166,6 +166,164 @@
       "eval_samples_per_second": 340.121,
       "eval_steps_per_second": 21.378,
       "step": 2000
+    },
+    {
+      "epoch": 0.042,
+      "grad_norm": 0.46283307671546936,
+      "learning_rate": 0.0005977398446852161,
+      "loss": 4.379761352539062,
+      "step": 2100
+    },
+    {
+      "epoch": 0.044,
+      "grad_norm": 0.3387432396411896,
+      "learning_rate": 0.0005975022955874992,
+      "loss": 4.3154080200195315,
+      "step": 2200
+    },
+    {
+      "epoch": 0.046,
+      "grad_norm": 0.2719409465789795,
+      "learning_rate": 0.0005972529308211201,
+      "loss": 4.275622863769531,
+      "step": 2300
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.2836616039276123,
+      "learning_rate": 0.0005969917602899061,
+      "loss": 4.258504333496094,
+      "step": 2400
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.32210105657577515,
+      "learning_rate": 0.0005967187943665656,
+      "loss": 4.207368469238281,
+      "step": 2500
+    },
+    {
+      "epoch": 0.052,
+      "grad_norm": 0.30050167441368103,
+      "learning_rate": 0.0005964340438922749,
+      "loss": 4.2094793701171875,
+      "step": 2600
+    },
+    {
+      "epoch": 0.054,
+      "grad_norm": 0.3175508379936218,
+      "learning_rate": 0.0005961375201762486,
+      "loss": 4.171758117675782,
+      "step": 2700
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.285259872674942,
+      "learning_rate": 0.0005958292349952897,
+      "loss": 4.1502682495117185,
+      "step": 2800
+    },
+    {
+      "epoch": 0.058,
+      "grad_norm": 0.2848680913448334,
+      "learning_rate": 0.0005955092005933225,
+      "loss": 4.128558959960937,
+      "step": 2900
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.2977091073989868,
+      "learning_rate": 0.000595177429680906,
+      "loss": 4.134291076660157,
+      "step": 3000
+    },
+    {
+      "epoch": 0.06,
+      "eval_accuracy": 0.3091028793639367,
+      "eval_loss": 4.053634166717529,
+      "eval_runtime": 6.2016,
+      "eval_samples_per_second": 312.982,
+      "eval_steps_per_second": 19.672,
+      "step": 3000
+    },
+    {
+      "epoch": 0.062,
+      "grad_norm": 0.2866455018520355,
+      "learning_rate": 0.0005948339354347288,
+      "loss": 4.118316040039063,
+      "step": 3100
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.2707529664039612,
+      "learning_rate": 0.0005944787314970865,
+      "loss": 4.104917602539063,
+      "step": 3200
+    },
+    {
+      "epoch": 0.066,
+      "grad_norm": 0.3138796091079712,
+      "learning_rate": 0.0005941118319753391,
+      "loss": 4.084369506835937,
+      "step": 3300
+    },
+    {
+      "epoch": 0.068,
+      "grad_norm": 0.2631393373012543,
+      "learning_rate": 0.0005937332514413514,
+      "loss": 4.044774475097657,
+      "step": 3400
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.27509307861328125,
+      "learning_rate": 0.0005933430049309136,
+      "loss": 4.025779418945312,
+      "step": 3500
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.33931243419647217,
+      "learning_rate": 0.0005929411079431449,
+      "loss": 4.004125366210937,
+      "step": 3600
+    },
+    {
+      "epoch": 0.074,
+      "grad_norm": 0.2669001519680023,
+      "learning_rate": 0.000592527576439877,
+      "loss": 4.012510070800781,
+      "step": 3700
+    },
+    {
+      "epoch": 0.076,
+      "grad_norm": 0.2727104425430298,
+      "learning_rate": 0.000592102426845021,
+      "loss": 3.9971853637695314,
+      "step": 3800
+    },
+    {
+      "epoch": 0.078,
+      "grad_norm": 0.25884559750556946,
+      "learning_rate": 0.0005916656760439145,
+      "loss": 3.9807003784179686,
+      "step": 3900
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3023005425930023,
+      "learning_rate": 0.0005912173413826517,
+      "loss": 3.9553176879882814,
+      "step": 4000
+    },
+    {
+      "epoch": 0.08,
+      "eval_accuracy": 0.32060359872601835,
+      "eval_loss": 3.923754930496216,
+      "eval_runtime": 6.2736,
+      "eval_samples_per_second": 309.393,
+      "eval_steps_per_second": 19.447,
+      "step": 4000
     }
   ],
   "logging_steps": 100,
@@ -185,7 +343,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.271008768e+16,
+  "total_flos": 1.2542017536e+17,
   "train_batch_size": 120,
   "trial_name": null,
   "trial_params": null