Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97bd4163198baf497e7b4a8abf3c917c56e9716628f424827646fc2b82ad66c2
+oid sha256:26933aacb8d89173c007714c72382eab969164100033536dab690ba95de7599a
 size 228140600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cbfc2ea55f5c437cdf9ee644d95ff2e6022b4072a7a97cf4682c55fe467d231
+oid sha256:006c4c9ba7fbfc9cd22c95bea73dc8f96274fb078eb4c40ebd9e2a0be6dce6b4
 size 116472340

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ac30eb90771ad572928492a9b294c2a00ae840bf4dd4ced4785e131650bb6d2
+oid sha256:e7d9dcffaabcac06de4bae4afd36f4c01b83e291513e2a9d27482c677edc84aa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
+oid sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.30927835051546393,
+  "epoch": 0.3402061855670103,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 6.836,
       "eval_steps_per_second": 0.865,
       "step": 90
+    },
+    {
+      "epoch": 0.31958762886597936,
+      "grad_norm": 1.5607446432113647,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.7605,
+      "step": 93
+    },
+    {
+      "epoch": 0.32989690721649484,
+      "grad_norm": 1.7891669273376465,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.8084,
+      "step": 96
+    },
+    {
+      "epoch": 0.3402061855670103,
+      "grad_norm": 1.7857033014297485,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.8207,
+      "step": 99
+    },
+    {
+      "epoch": 0.3402061855670103,
+      "eval_loss": 0.7051608562469482,
+      "eval_runtime": 71.6692,
+      "eval_samples_per_second": 6.837,
+      "eval_steps_per_second": 0.865,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1964744587935744e+17,
+  "total_flos": 3.488102718898176e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null