Training in progress, step 60, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94661efade50fe6aebdc27ba404c3ae586977e95a0a5743328cfd154ad1fc910
+oid sha256:155968869fcca097b33aaf908240b52fd8118e8fa88db2b3c2604bacade85ac1
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed634c87695c3354020e98afbf649d6ef58b6c85d097e57430eb83fe04ceb0eb
+oid sha256:50397b505bb135379928c86c3229e296d07221c0a9051ba1a7a679e11bada8c3
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9d8ba6dc294a7802a4dafc0e564c1a2eee3305104ad939fbc56d5ce507ea444
+oid sha256:55dcddf95f6df626baaef418beac8e8ae2cf66b3e94fecb344f33442737e8951
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f0cceb0ed85b2c6f37fd08e1761f95ce6ce00ab47aa275d076d6aa53a386d4e
+oid sha256:a64d4aece2607f1d3bc7ea4374d4260437623a49135c05801f0d688b2e80f254
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2204e8c1dd9dc7722a4f81e5fd4492d8dfa53c90fc9556f23dafd200a539a7a
+oid sha256:34c21f77637fb3f56ba02ef509b8a471991cc2ccccca6af51847140ee757415a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9003a850e509d15b02ef8ebe5e4de4ee92eba098365621434af147786d9f58d1
+oid sha256:a6687608b07c4a2d2152b65f49fc8bc54d8b4fc77151984b62a1a90d271ed6a0
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02fba4d221acb6fea331334b3de1974a87e216e52fc96554556bafda3bca4247
+oid sha256:f299ab56b5f200cab03608b3ac75cf1761ca29c2207c1dfe5ab919b66f8dbd88
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.666666666666667,
+  "epoch": 10.0,
   "eval_steps": 20,
-  "global_step": 40,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,28 @@
       "eval_samples_per_second": 646.597,
       "eval_steps_per_second": 5.169,
       "step": 40
+    },
+    {
+      "epoch": 8.333333333333334,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 10.2602,
+      "step": 50
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.326171875,
+      "learning_rate": 7.54514512859201e-05,
+      "loss": 10.2203,
+      "step": 60
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 10.208223342895508,
+      "eval_runtime": 2.3491,
+      "eval_samples_per_second": 638.981,
+      "eval_steps_per_second": 5.108,
+      "step": 60
     }
   ],
   "logging_steps": 10,
@@ -78,7 +100,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 32732683960320.0,
+  "total_flos": 49099025940480.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null