Training in progress, step 60, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca649e14cea98c3cc44061ac56285aa5df5d776c782a04bdb4bedbecc0733771
+oid sha256:3c1610b7eff6437eb2bb63e5dfdf8b49331eb71e4617388f7ffda9dbed527b51
 size 250490408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbe28617fceb4326d149bc2dffe3b42c8e87c0a1d3be8c4411e635fc5c164538
+oid sha256:e6e4c79a7e172ff7a4a912a2b1375c8d27c5c42763d3fae57a462b66c71b68d2
 size 255265850

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f7075b845fd2c310514c90a86f43f4a07f06ff68c6ffd9b017c704559836097
+oid sha256:143f5b4f9034575ed8875b5384514453e6af653a08c123c1e944efd394f8efc4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a34eaafb81fc29861f92562a49db625bc4b7b8bc7deb6e0900ac3e1e04fdbdfe
+oid sha256:b88ba6c6448836e3a8e625dcc4fe1c126d0b8f1a9400e26128b640c6a1a4e25e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:170259f6ec12ca458ff719ec610fe0ad1e4d444f8e1e1a9f502e530830402066
+oid sha256:2cb84bcc6e01403e7801ab46f03b72f577573daa0707f696fa7bd5ccf50adf21
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:003c71d0c6c30c0b2b1aab044884386c3f92f2c7e02b567413122f0724c87ec1
+oid sha256:8b6871625d54b2a1c5dbdd4ab6f1b61571d8205213dfb7c2b7cfd35f43eefcc4
 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": 282.0,
       "eval_steps_per_second": 2.254,
       "step": 40
+    },
+    {
+      "epoch": 8.333333333333334,
+      "grad_norm": 3.859375,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 4.8062,
+      "step": 50
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.671875,
+      "learning_rate": 7.54514512859201e-05,
+      "loss": 4.6384,
+      "step": 60
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 3.1967086791992188,
+      "eval_runtime": 5.1843,
+      "eval_samples_per_second": 289.528,
+      "eval_steps_per_second": 2.315,
+      "step": 60
     }
   ],
   "logging_steps": 10,
@@ -78,7 +100,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5198666398695424.0,
+  "total_flos": 7772915579748352.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null