Training in progress, step 2400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33d28c6c3a9ac9d45519bd761cb3ca784198eb452f8a0d37069ce8907e034bb8
+oid sha256:b66fb8875620c1d893c5b045750378f9dc051da0533dfe4198352490d5d42af6
 size 393837600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:924d4999b2ddf9930b6977bba3ed319e6828bfc5503de6b403e6f468efe3e462
+oid sha256:dbc0f250dfea452d5d339cf30295ce9a0a8a09a879cfc1f531cfbf831be6d227
 size 787715403

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6acb2036ccf8392ee9b401ccde0bfa18aa02ab57b26c0bddd589a52f4acbca0
+oid sha256:e99d7b14894e397f721505cd3cbdbab552f4190ab700d5ccc0bb3c084f241b06
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50776de256e512841eb4c81dd3a08c8ea0f67338b43976d8a7c46cd32080c140
+oid sha256:54e1ab90e8357c58bc510057c5c342975ffa0ea562e7fe289a4493739fdcb803
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c7f21054a238e4b4aeb2aeb8ad33c1ad5a1dc96f1e2a0057f1f421a1820a8c9
+oid sha256:10e81800bb418447855f5cca54cd6427b5425167cdb6bd1a392996b7d83e3e37
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012854747199710184,
+  "epoch": 0.014023360581502019,
   "eval_steps": 500,
-  "global_step": 2200,
+  "global_step": 2400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1548,6 +1548,146 @@
       "learning_rate": 0.0001794876799169918,
       "loss": 35.723779296875,
       "step": 2200
+    },
+    {
+      "epoch": 0.012913177868799775,
+      "grad_norm": 14303.4931640625,
+      "learning_rate": 0.0001794815758842455,
+      "loss": 34.96857604980469,
+      "step": 2210
+    },
+    {
+      "epoch": 0.012971608537889368,
+      "grad_norm": 7816.142578125,
+      "learning_rate": 0.0001794754358083311,
+      "loss": 36.672998046875,
+      "step": 2220
+    },
+    {
+      "epoch": 0.013030039206978958,
+      "grad_norm": 6360.27978515625,
+      "learning_rate": 0.0001794692596917219,
+      "loss": 36.156802368164065,
+      "step": 2230
+    },
+    {
+      "epoch": 0.013088469876068551,
+      "grad_norm": 9623.060546875,
+      "learning_rate": 0.00017946304753690558,
+      "loss": 36.09114379882813,
+      "step": 2240
+    },
+    {
+      "epoch": 0.013146900545158142,
+      "grad_norm": 7583.41796875,
+      "learning_rate": 0.0001794567993463844,
+      "loss": 37.17391357421875,
+      "step": 2250
+    },
+    {
+      "epoch": 0.013205331214247735,
+      "grad_norm": 10694.111328125,
+      "learning_rate": 0.00017945051512267517,
+      "loss": 35.996463012695315,
+      "step": 2260
+    },
+    {
+      "epoch": 0.013263761883337326,
+      "grad_norm": 8491.396484375,
+      "learning_rate": 0.00017944419486830914,
+      "loss": 35.70230712890625,
+      "step": 2270
+    },
+    {
+      "epoch": 0.013322192552426919,
+      "grad_norm": 9370.09375,
+      "learning_rate": 0.0001794378385858321,
+      "loss": 35.24028625488281,
+      "step": 2280
+    },
+    {
+      "epoch": 0.01338062322151651,
+      "grad_norm": 9418.51953125,
+      "learning_rate": 0.00017943144627780434,
+      "loss": 36.02164916992187,
+      "step": 2290
+    },
+    {
+      "epoch": 0.013439053890606102,
+      "grad_norm": 10567.708984375,
+      "learning_rate": 0.00017942501794680077,
+      "loss": 34.88120727539062,
+      "step": 2300
+    },
+    {
+      "epoch": 0.013497484559695693,
+      "grad_norm": 10314.2666015625,
+      "learning_rate": 0.00017941855359541062,
+      "loss": 35.403176879882814,
+      "step": 2310
+    },
+    {
+      "epoch": 0.013555915228785284,
+      "grad_norm": 7253.47021484375,
+      "learning_rate": 0.0001794120532262378,
+      "loss": 34.77778015136719,
+      "step": 2320
+    },
+    {
+      "epoch": 0.013614345897874877,
+      "grad_norm": 10410.0029296875,
+      "learning_rate": 0.00017940551684190068,
+      "loss": 35.402523803710935,
+      "step": 2330
+    },
+    {
+      "epoch": 0.013672776566964468,
+      "grad_norm": 4923.6806640625,
+      "learning_rate": 0.000179398944445032,
+      "loss": 35.451840209960935,
+      "step": 2340
+    },
+    {
+      "epoch": 0.01373120723605406,
+      "grad_norm": 13957.7392578125,
+      "learning_rate": 0.0001793923360382792,
+      "loss": 35.127255249023435,
+      "step": 2350
+    },
+    {
+      "epoch": 0.013789637905143651,
+      "grad_norm": 60150.3359375,
+      "learning_rate": 0.00017938569162430414,
+      "loss": 35.594277954101564,
+      "step": 2360
+    },
+    {
+      "epoch": 0.013848068574233244,
+      "grad_norm": 5336.36865234375,
+      "learning_rate": 0.0001793790112057832,
+      "loss": 36.180422973632815,
+      "step": 2370
+    },
+    {
+      "epoch": 0.013906499243322835,
+      "grad_norm": 10817.921875,
+      "learning_rate": 0.00017937229478540723,
+      "loss": 35.167120361328124,
+      "step": 2380
+    },
+    {
+      "epoch": 0.013964929912412428,
+      "grad_norm": 9958.671875,
+      "learning_rate": 0.00017936554236588158,
+      "loss": 34.59622802734375,
+      "step": 2390
+    },
+    {
+      "epoch": 0.014023360581502019,
+      "grad_norm": 10780.3876953125,
+      "learning_rate": 0.00017935875394992619,
+      "loss": 35.40941162109375,
+      "step": 2400
     }
   ],
   "logging_steps": 10,
@@ -1567,7 +1707,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.764054302241792e+16,
+  "total_flos": 1.9246210358102016e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null