Training in progress, step 60, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0af0e3452e1dd4f2872d97862892d5f7780935c9cca688534e4358ecd6f913a9
+oid sha256:1a8155ca2cd99302c7fad993e48147786844b315af548c9cb7f8a484fbfe0ee7
 size 28130688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d48098e754298a2a5e4f2d3490d1a8344bad1094a06f57f4db1a43e07de618f
+oid sha256:34828f777c0a17619737cc90816c07ba96ce3c8af3b590b738430c821f4c87de
 size 28684730

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": 302.115,
       "eval_steps_per_second": 2.415,
       "step": 40
+    },
+    {
+      "epoch": 8.333333333333334,
+      "grad_norm": 153.0,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 9.48,
+      "step": 50
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 86.0,
+      "learning_rate": 7.54514512859201e-05,
+      "loss": 9.1399,
+      "step": 60
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 8.825699806213379,
+      "eval_runtime": 4.9276,
+      "eval_samples_per_second": 304.609,
+      "eval_steps_per_second": 2.435,
+      "step": 60
     }
   ],
   "logging_steps": 10,
@@ -78,7 +100,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 468415307317248.0,
+  "total_flos": 700702070407168.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null