Training in progress, step 140, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7099eb40b413f475a94c7b20e0d010ecdee8502cbf1f8f85376025251705606
+oid sha256:ce2f1aa30d5eaf619a3c3e017ed7754121c2ff6be4a774b7691ecc396037c065
 size 2471645608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:262fc41bd3ed1fef91b75c67bb0b2e3125e07ecb1d82091bb9bbccf8d8c1295a
+oid sha256:6013018172e8e90f92a7185ecf6723b6d10af651282732a0570dc64f8a2bf781
 size 2510806010

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aa84ca9d29402ea2e0b68b9b09d2cb0e5d44ffa6a40c5cc9bba11a1fcc9f06a
+oid sha256:95a0836ed1d1df6a39c52676c50033899f159b2a086f39809f42b2abd08f98f0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83c7fe674fb900726179942ac72aa6448c71ebe6b10979088cbb7c4a6fe24949
+oid sha256:72d2f8d4dea78d8ee147023f016cd12fb983dd12869b55735aa35f72144a70de
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74686c6d7afa0a6e1d6a9460f587f954106c4f1ea317616d19962a2784f7358d
+oid sha256:c7fda2e4ac7ffb91a3ce7e64ea0fe5ed42405c8bcbef18e553f63be66a77fd54
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d80a7db13242e51c8bbd0c9438d518bc627260abe7ae1823adc2bf06096c9142
+oid sha256:5c98375c9f86a164b7cbbec77ff4614c1313758d8ac8dedbf96faa1321c4d161
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:013c01134f854276f29a5e5d6bd48f6e6752535a0847f5335cbcba030ae10220
+oid sha256:a58dce7b667be31a2849f694e1ec67799fde1d5a6e26353e473a211f9c6e2b03
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.0588235294117645,
+  "epoch": 8.235294117647058,
   "eval_steps": 20,
-  "global_step": 120,
+  "global_step": 140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,28 @@
       "eval_samples_per_second": 102.998,
       "eval_steps_per_second": 2.402,
       "step": 120
+    },
+    {
+      "epoch": 7.647058823529412,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.0001614212712689668,
+      "loss": 0.0733,
+      "step": 130
+    },
+    {
+      "epoch": 8.235294117647058,
+      "grad_norm": 0.69921875,
+      "learning_rate": 0.00015469481581224272,
+      "loss": 0.0776,
+      "step": 140
+    },
+    {
+      "epoch": 8.235294117647058,
+      "eval_loss": 3.6323835849761963,
+      "eval_runtime": 14.197,
+      "eval_samples_per_second": 105.726,
+      "eval_steps_per_second": 2.465,
+      "step": 140
     }
   ],
   "logging_steps": 10,
@@ -166,7 +188,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.25763179036672e+16,
+  "total_flos": 7.301566917142118e+16,
   "train_batch_size": 11,
   "trial_name": null,
   "trial_params": null