Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66bf7ec1906085b9017dec52af7ee1d8cb6d38fa8ca3a526334a82ecc740dcbd
+oid sha256:18fbd19ed0f067cccc4ceafafda68adefb55ef97f98832eadcfde47b3a2daf58
 size 2708729576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f48d93af9f829aae4cbfe51ee4fffab7189d58377b64586f31b892a561403e60
+oid sha256:51187af1a65ecfea4a3ff1628941e84133eca5a8394cb465996a300d69d54302
 size 52499200

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:838e024e0a852529a2257dc1dc52b7019dd292f53abc55b9fa61835eb1065232
+oid sha256:0d15855cc66c2961c5cc037b181eb659abb2ac26d92d4c28480e27683e47e34e
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bca4dbe650e04bc8012dd3f1938dfb2a637329721abd75c3bd59d28a64007b54
+oid sha256:0e8b7bfccb9c07860bceffabef3a52060cc451a19d3abd90d284c09f7120dba6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
+  "epoch": 2.0,
   "eval_steps": 10,
-  "global_step": 129,
+  "global_step": 258,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,6 +175,188 @@
       "eval_samples_per_second": 21.876,
       "eval_steps_per_second": 5.469,
       "step": 120
+    },
+    {
+      "epoch": 1.0078086871644705,
+      "grad_norm": 307601.53125,
+      "learning_rate": 8.984375e-05,
+      "loss": 3748.8004,
+      "step": 130
+    },
+    {
+      "epoch": 1.0078086871644705,
+      "eval_runtime": 19.6206,
+      "eval_samples_per_second": 22.018,
+      "eval_steps_per_second": 5.504,
+      "step": 130
+    },
+    {
+      "epoch": 1.0858955588091752,
+      "grad_norm": 535453.9375,
+      "learning_rate": 8.90625e-05,
+      "loss": 3701.0125,
+      "step": 140
+    },
+    {
+      "epoch": 1.0858955588091752,
+      "eval_runtime": 19.714,
+      "eval_samples_per_second": 21.913,
+      "eval_steps_per_second": 5.478,
+      "step": 140
+    },
+    {
+      "epoch": 1.16398243045388,
+      "grad_norm": 578524.75,
+      "learning_rate": 8.828125000000001e-05,
+      "loss": 3222.8713,
+      "step": 150
+    },
+    {
+      "epoch": 1.16398243045388,
+      "eval_runtime": 19.7417,
+      "eval_samples_per_second": 21.883,
+      "eval_steps_per_second": 5.471,
+      "step": 150
+    },
+    {
+      "epoch": 1.2420693020985847,
+      "grad_norm": 413461.9375,
+      "learning_rate": 8.75e-05,
+      "loss": 3225.8557,
+      "step": 160
+    },
+    {
+      "epoch": 1.2420693020985847,
+      "eval_runtime": 19.7549,
+      "eval_samples_per_second": 21.868,
+      "eval_steps_per_second": 5.467,
+      "step": 160
+    },
+    {
+      "epoch": 1.3201561737432894,
+      "grad_norm": 473611.9375,
+      "learning_rate": 8.671875e-05,
+      "loss": 2951.6514,
+      "step": 170
+    },
+    {
+      "epoch": 1.3201561737432894,
+      "eval_runtime": 19.7505,
+      "eval_samples_per_second": 21.873,
+      "eval_steps_per_second": 5.468,
+      "step": 170
+    },
+    {
+      "epoch": 1.3982430453879942,
+      "grad_norm": 477603.59375,
+      "learning_rate": 8.593750000000001e-05,
+      "loss": 3479.666,
+      "step": 180
+    },
+    {
+      "epoch": 1.3982430453879942,
+      "eval_runtime": 19.7691,
+      "eval_samples_per_second": 21.852,
+      "eval_steps_per_second": 5.463,
+      "step": 180
+    },
+    {
+      "epoch": 1.476329917032699,
+      "grad_norm": 284746.375,
+      "learning_rate": 8.515625e-05,
+      "loss": 2754.5521,
+      "step": 190
+    },
+    {
+      "epoch": 1.476329917032699,
+      "eval_runtime": 19.7613,
+      "eval_samples_per_second": 21.861,
+      "eval_steps_per_second": 5.465,
+      "step": 190
+    },
+    {
+      "epoch": 1.5544167886774036,
+      "grad_norm": 583813.5625,
+      "learning_rate": 8.4375e-05,
+      "loss": 1812.6566,
+      "step": 200
+    },
+    {
+      "epoch": 1.5544167886774036,
+      "eval_runtime": 19.7512,
+      "eval_samples_per_second": 21.872,
+      "eval_steps_per_second": 5.468,
+      "step": 200
+    },
+    {
+      "epoch": 1.6325036603221084,
+      "grad_norm": 277886.28125,
+      "learning_rate": 8.359375000000001e-05,
+      "loss": 2136.5822,
+      "step": 210
+    },
+    {
+      "epoch": 1.6325036603221084,
+      "eval_runtime": 19.746,
+      "eval_samples_per_second": 21.878,
+      "eval_steps_per_second": 5.469,
+      "step": 210
+    },
+    {
+      "epoch": 1.710590531966813,
+      "grad_norm": 322902.34375,
+      "learning_rate": 8.28125e-05,
+      "loss": 2078.6055,
+      "step": 220
+    },
+    {
+      "epoch": 1.710590531966813,
+      "eval_runtime": 19.7299,
+      "eval_samples_per_second": 21.896,
+      "eval_steps_per_second": 5.474,
+      "step": 220
+    },
+    {
+      "epoch": 1.7886774036115178,
+      "grad_norm": 453730.34375,
+      "learning_rate": 8.203125e-05,
+      "loss": 2769.8313,
+      "step": 230
+    },
+    {
+      "epoch": 1.7886774036115178,
+      "eval_runtime": 19.7557,
+      "eval_samples_per_second": 21.867,
+      "eval_steps_per_second": 5.467,
+      "step": 230
+    },
+    {
+      "epoch": 1.8667642752562226,
+      "grad_norm": 267086.625,
+      "learning_rate": 8.125000000000001e-05,
+      "loss": 1964.433,
+      "step": 240
+    },
+    {
+      "epoch": 1.8667642752562226,
+      "eval_runtime": 19.7438,
+      "eval_samples_per_second": 21.88,
+      "eval_steps_per_second": 5.47,
+      "step": 240
+    },
+    {
+      "epoch": 1.9448511469009273,
+      "grad_norm": 587362.4375,
+      "learning_rate": 8.046875e-05,
+      "loss": 1856.9432,
+      "step": 250
+    },
+    {
+      "epoch": 1.9448511469009273,
+      "eval_runtime": 19.8026,
+      "eval_samples_per_second": 21.815,
+      "eval_steps_per_second": 5.454,
+      "step": 250
     }
   ],
   "logging_steps": 10,