Training in progress, step 15500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7454f4d66c270e44df1eacbd6185e4004d87782931028de1f535c0307f116fd
+oid sha256:2e4c46a908162b00f3ba9486bea20fb84fb3214d554c60ceeedafb0b57bf2240
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ad72731605d1660caf040ca225055f57942f6652ac3f8e3f4a48d6e14eb50fd
+oid sha256:99c44c9279a3a25aea078d1e884539b925aea0259a9d1b9cea8a21f053a5066d
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94a590caf5b0791267c7c662cc1f8162ae428b45baf48632e99e270be42d5011
+oid sha256:13d5ccf4326b5409b6c9f169af8a58a6579e0381579d71b37aaa359b3cba5d5e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d713a762ef6487a34237b674f0e37296a124b258ea254d4be9d4a61b4da657a1
+oid sha256:3bd47cad1117d63c0c537ebb025d165a0cc6ebd76cda442e82a66a6ac283ef01
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
+  "epoch": 1.0333333333333334,
   "eval_steps": 500,
-  "global_step": 15000,
+  "global_step": 15500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1057,6 +1057,49 @@
       "learning_rate": 1.3335111111111113e-05,
       "loss": 0.0651,
       "step": 15000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.08444427698850632,
+      "eval_runtime": 120.3607,
+      "eval_samples_per_second": 16.617,
+      "eval_steps_per_second": 4.154,
+      "step": 15000
+    },
+    {
+      "epoch": 1.0066666666666666,
+      "grad_norm": 0.23236271739006042,
+      "learning_rate": 1.3290666666666668e-05,
+      "loss": 0.0578,
+      "step": 15100
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 0.3065841794013977,
+      "learning_rate": 1.3246222222222223e-05,
+      "loss": 0.0586,
+      "step": 15200
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.10468995571136475,
+      "learning_rate": 1.3201777777777778e-05,
+      "loss": 0.0562,
+      "step": 15300
+    },
+    {
+      "epoch": 1.0266666666666666,
+      "grad_norm": 0.12645235657691956,
+      "learning_rate": 1.3157333333333335e-05,
+      "loss": 0.0595,
+      "step": 15400
+    },
+    {
+      "epoch": 1.0333333333333334,
+      "grad_norm": 0.22408919036388397,
+      "learning_rate": 1.311288888888889e-05,
+      "loss": 0.0703,
+      "step": 15500
     }
   ],
   "logging_steps": 100,
@@ -1076,7 +1119,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.65374734336e+16,
+  "total_flos": 3.775538921472e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null