Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd96db79c4222be60ac97ed313bf003c743cde5a7a5c4b544170bfe9a38918ab
+oid sha256:43a9360070c3bc7665329ef6cb9c18a8e89dccf07afbcce13c03aaa1b9135b86
 size 2026568872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:836e1bb9ed04bb2bb4d304d7b680e054ec780785a9b452982b60c396c2ef8eab
+oid sha256:2279e40a4763df41f0c4bffc85edce65759b20ec629561bfa04dd1975a601194
 size 4053320058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37c40ce327861a7ca13b719d3aa37510a143368b6e74358bdb14becb3899e1e
+oid sha256:95b6047bd8cc6f4cdf7c46dea47edb8e542435510070c6cd1e0a7d9ccf5fd7da
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8469d184647c045d6d08f5cb32f7cd8ed66023f5033c0b4e25a0f6783d7d6ba9
+oid sha256:272640d7b61b2124df30234bf0964b9c0109c8e0621189f0064bc693bd54a0bb
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.3774104683195592,
+  "epoch": 2.7548209366391183,
   "eval_steps": 363,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -94,6 +94,84 @@
       "learning_rate": 0.00019964161211349086,
       "loss": 3.9705,
       "step": 500
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "grad_norm": 8.101067543029785,
+      "learning_rate": 0.00019956463117038584,
+      "loss": 3.9586,
+      "step": 550
+    },
+    {
+      "epoch": 1.6528925619834711,
+      "grad_norm": 5.826588153839111,
+      "learning_rate": 0.00019948018457833974,
+      "loss": 3.9575,
+      "step": 600
+    },
+    {
+      "epoch": 1.790633608815427,
+      "grad_norm": 6.841236114501953,
+      "learning_rate": 0.00019938827866940642,
+      "loss": 3.9663,
+      "step": 650
+    },
+    {
+      "epoch": 1.9283746556473829,
+      "grad_norm": 7.117630481719971,
+      "learning_rate": 0.0001992889203349613,
+      "loss": 3.9456,
+      "step": 700
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 4.049391269683838,
+      "eval_runtime": 70.275,
+      "eval_samples_per_second": 6.916,
+      "eval_steps_per_second": 6.916,
+      "step": 726
+    },
+    {
+      "epoch": 2.0661157024793386,
+      "grad_norm": 6.624067783355713,
+      "learning_rate": 0.00019918211702518463,
+      "loss": 3.789,
+      "step": 750
+    },
+    {
+      "epoch": 2.203856749311295,
+      "grad_norm": 5.628150463104248,
+      "learning_rate": 0.00019906787674850275,
+      "loss": 3.6285,
+      "step": 800
+    },
+    {
+      "epoch": 2.3415977961432506,
+      "grad_norm": 5.53456974029541,
+      "learning_rate": 0.00019894620807098763,
+      "loss": 3.6531,
+      "step": 850
+    },
+    {
+      "epoch": 2.479338842975207,
+      "grad_norm": 4.971586227416992,
+      "learning_rate": 0.00019881712011571466,
+      "loss": 3.6592,
+      "step": 900
+    },
+    {
+      "epoch": 2.6170798898071626,
+      "grad_norm": 5.7469801902771,
+      "learning_rate": 0.0001986806225620785,
+      "loss": 3.6672,
+      "step": 950
+    },
+    {
+      "epoch": 2.7548209366391183,
+      "grad_norm": 4.165513038635254,
+      "learning_rate": 0.00019853672564506725,
+      "loss": 3.6785,
+      "step": 1000
     }
   ],
   "logging_steps": 50,
@@ -113,7 +191,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8795704000512000.0,
+  "total_flos": 1.7591408001024e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null