Training in progress, step 35, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e313dae42c4d8192fa932173cce577e54ece11b24db4927e11d57cdd6d4df56
+oid sha256:c350e1f2133ebde280250f16e555217050fbcdd181b4658a3fed0009cfdbe4b3
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a6678bf0aa2b0ca5080f7a9607b564dd8ad41229bf3d39d455f12c26820e6f6
+oid sha256:2fc8e1e90760c6e0f40101fb231cafce2834dd861dfedea311821459d265768a
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e97ead28242dd097af80112cb3bd8d751944021cbf255fca1535e0f2a22344d9
+oid sha256:005d9a86e0834fe0802ab2e1c3fa9eca806e3cae26d1cbb14ab848a758219c13
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18691588785046728,
+  "epoch": 0.6542056074766355,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 35,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,102 @@
       "eval_samples_per_second": 529.918,
       "eval_steps_per_second": 70.656,
       "step": 10
+    },
+    {
+      "epoch": 0.22429906542056074,
+      "grad_norm": 0.042363181710243225,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 10.379,
+      "step": 12
+    },
+    {
+      "epoch": 0.2803738317757009,
+      "grad_norm": 0.04922573268413544,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 10.3784,
+      "step": 15
+    },
+    {
+      "epoch": 0.2803738317757009,
+      "eval_loss": 10.377721786499023,
+      "eval_runtime": 0.1729,
+      "eval_samples_per_second": 520.526,
+      "eval_steps_per_second": 69.404,
+      "step": 15
+    },
+    {
+      "epoch": 0.3364485981308411,
+      "grad_norm": 0.04994016885757446,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 10.3767,
+      "step": 18
+    },
+    {
+      "epoch": 0.37383177570093457,
+      "eval_loss": 10.37624454498291,
+      "eval_runtime": 0.1945,
+      "eval_samples_per_second": 462.625,
+      "eval_steps_per_second": 61.683,
+      "step": 20
+    },
+    {
+      "epoch": 0.3925233644859813,
+      "grad_norm": 0.06224982813000679,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 10.3755,
+      "step": 21
+    },
+    {
+      "epoch": 0.4485981308411215,
+      "grad_norm": 0.07088863849639893,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 10.3739,
+      "step": 24
+    },
+    {
+      "epoch": 0.4672897196261682,
+      "eval_loss": 10.374489784240723,
+      "eval_runtime": 0.1721,
+      "eval_samples_per_second": 522.823,
+      "eval_steps_per_second": 69.71,
+      "step": 25
+    },
+    {
+      "epoch": 0.5046728971962616,
+      "grad_norm": 0.08333060145378113,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 10.3734,
+      "step": 27
+    },
+    {
+      "epoch": 0.5607476635514018,
+      "grad_norm": 0.08638530224561691,
+      "learning_rate": 5e-05,
+      "loss": 10.3719,
+      "step": 30
+    },
+    {
+      "epoch": 0.5607476635514018,
+      "eval_loss": 10.372705459594727,
+      "eval_runtime": 0.1771,
+      "eval_samples_per_second": 508.112,
+      "eval_steps_per_second": 67.748,
+      "step": 30
+    },
+    {
+      "epoch": 0.616822429906542,
+      "grad_norm": 0.09677360951900482,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 10.3714,
+      "step": 33
+    },
+    {
+      "epoch": 0.6542056074766355,
+      "eval_loss": 10.371152877807617,
+      "eval_runtime": 0.1738,
+      "eval_samples_per_second": 517.918,
+      "eval_steps_per_second": 69.056,
+      "step": 35
     }
   ],
   "logging_steps": 3,
@@ -71,7 +167,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1115506606080.0,
+  "total_flos": 3904273121280.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null