Training in progress, step 120, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:477cfaff796c242d39f2bb4581392bf40cc2b118c07d4b549f30d58fe0a28c97
+oid sha256:b7099eb40b413f475a94c7b20e0d010ecdee8502cbf1f8f85376025251705606
 size 2471645608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99b8bfbfcc96c1c0bfcc15474791aa792c830c3c3f0f9761c4dadc6a54009aa0
+oid sha256:262fc41bd3ed1fef91b75c67bb0b2e3125e07ecb1d82091bb9bbccf8d8c1295a
 size 2510806010

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02a0dcb5af9028e2897c9593dde83af1664614071a7f75a707a055c6c1d4a6d0
+oid sha256:3aa84ca9d29402ea2e0b68b9b09d2cb0e5d44ffa6a40c5cc9bba11a1fcc9f06a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2af48b5aca2095d096bbbba55b03df2d5d5004081b32a23c149dddc409dab7ee
+oid sha256:83c7fe674fb900726179942ac72aa6448c71ebe6b10979088cbb7c4a6fe24949
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd3c4062e83c436475390f5677feae116fea7a05c2ea4dd2e74d24b626bb7fb7
+oid sha256:74686c6d7afa0a6e1d6a9460f587f954106c4f1ea317616d19962a2784f7358d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca7924a6ea6bb03da6e27fd733fc3268686d9e83baa69f58fce4c698e2bb91ab
+oid sha256:d80a7db13242e51c8bbd0c9438d518bc627260abe7ae1823adc2bf06096c9142
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d85c496fb1d6636ed23650fa58b39950c6ccced2da3e8f22df5d826a6c19d1a
+oid sha256:013c01134f854276f29a5e5d6bd48f6e6752535a0847f5335cbcba030ae10220
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.882352941176471,
+  "epoch": 7.0588235294117645,
   "eval_steps": 20,
-  "global_step": 100,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -125,6 +125,28 @@
       "eval_samples_per_second": 98.814,
       "eval_steps_per_second": 2.304,
       "step": 100
+    },
+    {
+      "epoch": 6.470588235294118,
+      "grad_norm": 1.1796875,
+      "learning_rate": 0.00017357239106731317,
+      "loss": 0.1188,
+      "step": 110
+    },
+    {
+      "epoch": 7.0588235294117645,
+      "grad_norm": 0.78125,
+      "learning_rate": 0.00016772815716257412,
+      "loss": 0.1193,
+      "step": 120
+    },
+    {
+      "epoch": 7.0588235294117645,
+      "eval_loss": 3.397793769836426,
+      "eval_runtime": 14.573,
+      "eval_samples_per_second": 102.998,
+      "eval_steps_per_second": 2.402,
+      "step": 120
     }
   ],
   "logging_steps": 10,
@@ -144,7 +166,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.223263112685158e+16,
+  "total_flos": 6.25763179036672e+16,
   "train_batch_size": 11,
   "trial_name": null,
   "trial_params": null