Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bf1d2a952d87403172e62da7597cdc8a96002c708f0a5e79d7de04f4584bf8e
+oid sha256:78653e639d0cc287b764d3d222838670f7dbf965eb14948b500a6255157066d3
 size 1324830880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b2edf4f04bf9b4035f407e950f30565e1809557f5a012ef19f0215deee1a206
+oid sha256:9c1808daacabf9fa41c3a7d7c6f4257314eb2226a8c16243fbe6a725fc426f8a
 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": 2.4022321701049805,
   "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": 13.787,
       "eval_steps_per_second": 1.723,
       "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
     }
   ],
   "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