Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6697b655f4d18a8afd09bb9096be4f1a913a0271400253530af3111df7c5aab
+oid sha256:db6bd1201607af974459ccd4065cd330ecc74220d99d6027ee518c958182b92a
 size 2610104820

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3379d3b2136cd08b2e8087edaea7dccb8c45d272e6cb1ff778c0d48eb147e4c
+oid sha256:2f72765dc0f4a81f457004ec2c30aed32c0ee47c8bf90accb3c37cdf1cdade6f
 size 5210004271

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b30662bbeef6882959d6b6e1aa2b4df9a78ead5291d63da14771bbe171fced3d
+oid sha256:6ed8d71e0753140beb986a58bf8f7796a167131509a31d6bb830cbf6a6613e20
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09d30be9f305b7f8107cd63b7c58a0bc8abb2ce2c79242a145a2911b000d0ccd
+oid sha256:fa16028b3a94e761d69303edbfc8b5005e3b0ea737921fd8bfef31f57a9dd3df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3613533973693848,
-  "best_model_checkpoint": "mgh6/HTH_prob/checkpoint-488",
-  "epoch": 1.9960454139558617,
+  "best_metric": 1.3529444932937622,
+  "best_model_checkpoint": "mgh6/HTH_prob/checkpoint-732",
+  "epoch": 2.9960454139558617,
   "eval_steps": 500,
-  "global_step": 488,
+  "global_step": 732,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,21 @@
       "eval_samples_per_second": 32.874,
       "eval_steps_per_second": 16.437,
       "step": 488
+    },
+    {
+      "epoch": 2.9960454139558617,
+      "grad_norm": 0.07232648879289627,
+      "learning_rate": 0.00095,
+      "loss": 1.3631,
+      "step": 732
+    },
+    {
+      "epoch": 2.9960454139558617,
+      "eval_loss": 1.3529444932937622,
+      "eval_runtime": 25.1711,
+      "eval_samples_per_second": 32.815,
+      "eval_steps_per_second": 16.408,
+      "step": 732
     }
   ],
   "logging_steps": 500,