Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f92496aae4e50218f17c408d9883e0b6631b5eec345e15dc4d75b8e3b39a5f39
+oid sha256:e85ad51a8f7791129aaf97fb561ce631105d810e38029b60c5e10b3ba81c6da6
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:897bf189cdb8886d28116188448a1b8194928f43fed0c2ceb003736fb174b1eb
+oid sha256:4dd5d1b79a35eeded8b6e9f489d2495c066c10b984eb7cb6d30a625c505a0da0
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f6cda69bfbe0de119defc83e5da3ac5af16a274455608c670b1651222f7fc96
+oid sha256:408a06755b519bb846de2707ae71844004b4b1bde9426470048a53e0c32a92b3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
+oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.20497803806734993,
+  "epoch": 0.2342606149341142,
   "eval_steps": 5,
-  "global_step": 35,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,28 @@
       "eval_samples_per_second": 15.6,
       "eval_steps_per_second": 1.95,
       "step": 35
+    },
+    {
+      "epoch": 0.2108345534407028,
+      "grad_norm": 8.859992980957031,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 1.908,
+      "step": 36
+    },
+    {
+      "epoch": 0.22840409956076135,
+      "grad_norm": 11.509817123413086,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 1.5966,
+      "step": 39
+    },
+    {
+      "epoch": 0.2342606149341142,
+      "eval_loss": 0.36830881237983704,
+      "eval_runtime": 18.4993,
+      "eval_samples_per_second": 15.568,
+      "eval_steps_per_second": 1.946,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -167,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.656780307070976e+16,
+  "total_flos": 5.322034636652544e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null