Training in progress, step 60, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed442eb760b6a5ae9ca7cc0929866dedc1b056ba91729d120f45744e91a8cc8a
+oid sha256:dd264370ec8116c7637706c9258994699d14569d41d8da7845c334f7b50ce369
 size 4140280

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97d9b156ab4d9c31a40ed8763db197ee8f46b5518205573afb153664b08e8589
+oid sha256:d0a896c905ae2851fd5619a41bac6532997acf6e410f4b5d3b8f4e5551100aa7
 size 4291766

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": 642.213,
       "eval_steps_per_second": 5.134,
       "step": 40
+    },
+    {
+      "epoch": 8.333333333333334,
+      "grad_norm": 0.4609375,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 10.0382,
+      "step": 50
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.4609375,
+      "learning_rate": 7.54514512859201e-05,
+      "loss": 9.9768,
+      "step": 60
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 9.960792541503906,
+      "eval_runtime": 2.3223,
+      "eval_samples_per_second": 646.34,
+      "eval_steps_per_second": 5.167,
+      "step": 60
     }
   ],
   "logging_steps": 10,
@@ -78,7 +100,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 65745211883520.0,
+  "total_flos": 98617817825280.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null