Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a8a3024efb86283d45bf5e453bf9b3ee550ffbcb666b8c543ff701600ed4e36
+oid sha256:2034bb97f4730139642eb3804cfcc23e3e7ae555351b5d9b5b1144ed6ab06648
 size 1324830880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd21516a72f5c0777916d38f22ea2887605313b61dc10dbcc9c16c1dfb188ddd
+oid sha256:3b5abddcf41715edb74a3561fb07fd74da8c594dec7a45ab2714cf75ed7b5996
 size 2649896030

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df28232a1de30d1b227c0efb54de7a0d430617f62ba514c9422d3e8b85d3ced8
+oid sha256:b19017691ba1183e28fdb61b4af9141a4d5260985dada79dc93c86adebcea5df
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dbf8f944ea194273642caaf2a78a4ac235bd542ada6976e2803f1735daa8e77
+oid sha256:16aae2bd78e4d4da557759bb72d80c4f5d11afb7de0a65ba2d7641cf4fc763af
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.431854248046875,
   "best_model_checkpoint": "./opt_trained1/checkpoint-268",
-  "epoch": 1.0,
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 268,
+  "global_step": 536,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -15,6 +15,21 @@
       "eval_samples_per_second": 13.788,
       "eval_steps_per_second": 1.724,
       "step": 268
+    },
+    {
+      "epoch": 1.8664799253034547,
+      "grad_norm": 312980.71875,
+      "learning_rate": 0.00036254681647940074,
+      "loss": 2.4781,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.474102258682251,
+      "eval_runtime": 207.1259,
+      "eval_samples_per_second": 13.789,
+      "eval_steps_per_second": 1.724,
+      "step": 536
     }
   ],
   "logging_steps": 500,
@@ -34,7 +49,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.809948514295808e+16,
+  "total_flos": 3.619897028591616e+16,
   "train_batch_size": 12,
   "trial_name": null,
   "trial_params": null