Training in progress, epoch 8, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12fc2fc95519e8c736ec6b3d0a77b3e25ed7c233e27f177ff101c766e80bf02b
+oid sha256:5562090f9fa1129f5aaa580645497e48d5abe9584fdafc530eeaf40813d77f16
 size 2609498088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c942f7fe65abeb2bdc8fc7396b9a17cc51c747caca3939743aa338298ee7e1d
+oid sha256:f2a1617dec427bfbc3ea454bf8d167fbc45ab9a7cba154e6897ed91525ad35dc
 size 5208796146

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9bd9a69f693e1a28c165ba6f898faeebbcaaab424a68e8c32fc40b36b9ff5e3
+oid sha256:839b1bf83e268fa72451a6eb1844dabdf138c04e5c6a0d00f0f415b37ecf6799
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1318a37534b462ff16790cf62c003bcdfdf0493594d4a0b3e928e4d2f7999ab
+oid sha256:98b9a9b66ad7c2c92d26ff031cce36ce8f9c2ebdb6be883784d837b0e0137568
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.0,
+  "epoch": 8.0,
   "eval_steps": 50,
-  "global_step": 903,
+  "global_step": 1032,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -277,6 +277,36 @@
       "eval_samples_per_second": 37.447,
       "eval_steps_per_second": 18.724,
       "step": 900
+    },
+    {
+      "epoch": 7.367008296730113,
+      "grad_norm": 0.7260088920593262,
+      "learning_rate": 2.578125e-05,
+      "loss": 1.0371,
+      "step": 950
+    },
+    {
+      "epoch": 7.367008296730113,
+      "eval_loss": 1.1634416580200195,
+      "eval_runtime": 11.5405,
+      "eval_samples_per_second": 37.433,
+      "eval_steps_per_second": 18.717,
+      "step": 950
+    },
+    {
+      "epoch": 7.7574426549536355,
+      "grad_norm": 0.6944181323051453,
+      "learning_rate": 2.1875e-05,
+      "loss": 1.0466,
+      "step": 1000
+    },
+    {
+      "epoch": 7.7574426549536355,
+      "eval_loss": 1.154969573020935,
+      "eval_runtime": 11.532,
+      "eval_samples_per_second": 37.461,
+      "eval_steps_per_second": 18.731,
+      "step": 1000
     }
   ],
   "logging_steps": 50,
@@ -296,7 +326,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4964225415774208e+17,
+  "total_flos": 2.8530543349569946e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null