Training in progress, epoch 1, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:237ea5d7854149f452a4042eb3cb3384e93dad7ff2cedcc30070e6c85751b750
+oid sha256:5a8a3024efb86283d45bf5e453bf9b3ee550ffbcb666b8c543ff701600ed4e36
 size 1324830880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3c84b5be4b9b401cb48770063f2517a0fdb5177a8bcff6db785fe7954febc72
+oid sha256:dd21516a72f5c0777916d38f22ea2887605313b61dc10dbcc9c16c1dfb188ddd
 size 2649896030

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb10c9d6bc9fa712342ab2014e39173dc6d0c92e3482143e2f8eef0197ae6c40
+oid sha256:df28232a1de30d1b227c0efb54de7a0d430617f62ba514c9422d3e8b85d3ced8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c441f68d34987b8578be1b29313268756039e66819fc49dbcf77e0d1c8721b2c
+oid sha256:2dbf8f944ea194273642caaf2a78a4ac235bd542ada6976e2803f1735daa8e77
 size 1064

last-checkpoint/trainer_state.json

@@ -1,58 +1,20 @@
 {
-  "best_metric": 2.4022321701049805,
+  "best_metric": 2.431854248046875,
   "best_model_checkpoint": "./opt_trained1/checkpoint-268",
-  "epoch": 4.0,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 1072,
+  "global_step": 268,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 2.4022321701049805,
-      "eval_runtime": 207.1452,
-      "eval_samples_per_second": 13.787,
-      "eval_steps_per_second": 1.723,
+      "eval_loss": 2.431854248046875,
+      "eval_runtime": 207.1314,
+      "eval_samples_per_second": 13.788,
+      "eval_steps_per_second": 1.724,
       "step": 268
-    },
-    {
-      "epoch": 1.8664799253034547,
-      "grad_norm": 563550.25,
-      "learning_rate": 0.00036254681647940074,
-      "loss": 2.4789,
-      "step": 500
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 2.4977777004241943,
-      "eval_runtime": 206.6301,
-      "eval_samples_per_second": 13.822,
-      "eval_steps_per_second": 1.728,
-      "step": 536
-    },
-    {
-      "epoch": 3.0,
-      "eval_loss": 6.932552814483643,
-      "eval_runtime": 207.3048,
-      "eval_samples_per_second": 13.777,
-      "eval_steps_per_second": 1.722,
-      "step": 804
-    },
-    {
-      "epoch": 3.7320261437908497,
-      "grad_norm": 295233.46875,
-      "learning_rate": 0.0003250936329588015,
-      "loss": 2.3989,
-      "step": 1000
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": 8.40062141418457,
-      "eval_runtime": 207.5232,
-      "eval_samples_per_second": 13.762,
-      "eval_steps_per_second": 1.72,
-      "step": 1072
     }
   ],
   "logging_steps": 500,
@@ -72,7 +34,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.239794057183232e+16,
+  "total_flos": 1.809948514295808e+16,
   "train_batch_size": 12,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5db2222136e05949276be8a807dc409239b47ab761a0c7e53aa25bc62897fc5
+oid sha256:e7ea0facaa868ab91cf2092a8d2d40baf30425ddd42bb13a273f26d1ab6a2382
 size 5368