Training in progress, epoch 5, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c7751852532bea042b2263fbba8baca9de4de27d4c0f909171d7de0df8e9e4e
+oid sha256:7ce7821ec3b1341079f163800e5fc9bce2fbb1e7d4d4cdd2ae9a6a8b38a62182
 size 2695611744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43d37c97cf33a62efa149776acf51b56f1c3990e618d8965859241c368921937
+oid sha256:0fe4d41ac7b00d65dea543dfa7308e90ce556f6fa4e0f49330583f49d272ebcf
 size 26261260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13a87652f696aae07a6616b1088616ece95dadb9b70d2197d96fbef272ac3457
+oid sha256:a45b784475c6c47021a6ff08c5d6a553172a50192f5de3c134961024cdbbaf9f
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0267fbad859e57b7ff33d6dbd4fbd9fdf3cbf25f82f07754a3b6e19cff3ef2f5
+oid sha256:b514faa73b6e320d8ae19d93f3da594146e59f1072af645ee09b9ce747afd0a1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.0,
+  "epoch": 5.0,
   "eval_steps": 10,
-  "global_step": 516,
+  "global_step": 645,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -721,6 +721,188 @@
       "eval_samples_per_second": 22.006,
       "eval_steps_per_second": 5.501,
       "step": 510
+    },
+    {
+      "epoch": 4.031234748657882,
+      "grad_norm": 255615.1875,
+      "learning_rate": 5.9375e-05,
+      "loss": 900.3142,
+      "step": 520
+    },
+    {
+      "epoch": 4.031234748657882,
+      "eval_runtime": 19.5145,
+      "eval_samples_per_second": 22.137,
+      "eval_steps_per_second": 5.534,
+      "step": 520
+    },
+    {
+      "epoch": 4.109321620302587,
+      "grad_norm": 318956.46875,
+      "learning_rate": 5.8593750000000005e-05,
+      "loss": 998.6581,
+      "step": 530
+    },
+    {
+      "epoch": 4.109321620302587,
+      "eval_runtime": 19.5902,
+      "eval_samples_per_second": 22.052,
+      "eval_steps_per_second": 5.513,
+      "step": 530
+    },
+    {
+      "epoch": 4.187408491947291,
+      "grad_norm": 291643.28125,
+      "learning_rate": 5.78125e-05,
+      "loss": 1226.5887,
+      "step": 540
+    },
+    {
+      "epoch": 4.187408491947291,
+      "eval_runtime": 19.6079,
+      "eval_samples_per_second": 22.032,
+      "eval_steps_per_second": 5.508,
+      "step": 540
+    },
+    {
+      "epoch": 4.265495363591996,
+      "grad_norm": 283195.4375,
+      "learning_rate": 5.703125e-05,
+      "loss": 1072.7449,
+      "step": 550
+    },
+    {
+      "epoch": 4.265495363591996,
+      "eval_runtime": 19.6116,
+      "eval_samples_per_second": 22.028,
+      "eval_steps_per_second": 5.507,
+      "step": 550
+    },
+    {
+      "epoch": 4.343582235236701,
+      "grad_norm": 335369.625,
+      "learning_rate": 5.6250000000000005e-05,
+      "loss": 801.423,
+      "step": 560
+    },
+    {
+      "epoch": 4.343582235236701,
+      "eval_runtime": 19.6203,
+      "eval_samples_per_second": 22.018,
+      "eval_steps_per_second": 5.505,
+      "step": 560
+    },
+    {
+      "epoch": 4.421669106881406,
+      "grad_norm": 363015.75,
+      "learning_rate": 5.546875e-05,
+      "loss": 1544.8841,
+      "step": 570
+    },
+    {
+      "epoch": 4.421669106881406,
+      "eval_runtime": 19.633,
+      "eval_samples_per_second": 22.004,
+      "eval_steps_per_second": 5.501,
+      "step": 570
+    },
+    {
+      "epoch": 4.49975597852611,
+      "grad_norm": 314545.34375,
+      "learning_rate": 5.46875e-05,
+      "loss": 1318.7243,
+      "step": 580
+    },
+    {
+      "epoch": 4.49975597852611,
+      "eval_runtime": 19.6216,
+      "eval_samples_per_second": 22.017,
+      "eval_steps_per_second": 5.504,
+      "step": 580
+    },
+    {
+      "epoch": 4.577842850170815,
+      "grad_norm": 436113.09375,
+      "learning_rate": 5.3906250000000006e-05,
+      "loss": 1256.4427,
+      "step": 590
+    },
+    {
+      "epoch": 4.577842850170815,
+      "eval_runtime": 19.6143,
+      "eval_samples_per_second": 22.025,
+      "eval_steps_per_second": 5.506,
+      "step": 590
+    },
+    {
+      "epoch": 4.65592972181552,
+      "grad_norm": 307997.78125,
+      "learning_rate": 5.3125000000000004e-05,
+      "loss": 1325.2429,
+      "step": 600
+    },
+    {
+      "epoch": 4.65592972181552,
+      "eval_runtime": 19.6167,
+      "eval_samples_per_second": 22.022,
+      "eval_steps_per_second": 5.506,
+      "step": 600
+    },
+    {
+      "epoch": 4.7340165934602245,
+      "grad_norm": 383733.25,
+      "learning_rate": 5.234375e-05,
+      "loss": 1247.956,
+      "step": 610
+    },
+    {
+      "epoch": 4.7340165934602245,
+      "eval_runtime": 19.6214,
+      "eval_samples_per_second": 22.017,
+      "eval_steps_per_second": 5.504,
+      "step": 610
+    },
+    {
+      "epoch": 4.812103465104929,
+      "grad_norm": 434974.0,
+      "learning_rate": 5.15625e-05,
+      "loss": 1198.3052,
+      "step": 620
+    },
+    {
+      "epoch": 4.812103465104929,
+      "eval_runtime": 19.6132,
+      "eval_samples_per_second": 22.026,
+      "eval_steps_per_second": 5.506,
+      "step": 620
+    },
+    {
+      "epoch": 4.890190336749634,
+      "grad_norm": 182716.515625,
+      "learning_rate": 5.0781250000000004e-05,
+      "loss": 853.0629,
+      "step": 630
+    },
+    {
+      "epoch": 4.890190336749634,
+      "eval_runtime": 19.618,
+      "eval_samples_per_second": 22.021,
+      "eval_steps_per_second": 5.505,
+      "step": 630
+    },
+    {
+      "epoch": 4.968277208394339,
+      "grad_norm": 364455.15625,
+      "learning_rate": 5e-05,
+      "loss": 798.3182,
+      "step": 640
+    },
+    {
+      "epoch": 4.968277208394339,
+      "eval_runtime": 19.6019,
+      "eval_samples_per_second": 22.039,
+      "eval_steps_per_second": 5.51,
+      "step": 640
     }
   ],
   "logging_steps": 10,