Training in progress, step 12, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6bf84be1aae5b8b7946457e506504c6c2630fdef4fb88e2464690ae66e14367
+oid sha256:b941437f8f5adc30c8d8b646f5ebdca65d629aab45b5bcf80694a63db90ee74d
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8cb4d027701d26930a17df48eb5d041515507f70e9aee259cd342d19580d93b
+oid sha256:f6818586f1bff931e6761d8ea528ec61ffce61d86735b2b0855555d43d0daf2a
 size 263088

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:738162faf052e4c539199a028fb652e4005a183b04a94b3c028ce4724481c2e6
+oid sha256:c26f365cac1317ac7717d8d7fed569b9ee8569217a3a63a2bff3f96ac3bc944b
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42db7237a248957f8ca1684b4d9fc99ed0496fe869a62d0c7eff835c4c03f07d
+oid sha256:9096a675bca03d3146bb2cbed300e224b12143889738fc5012a9f7cd4ddeb71f
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c4ce4d091756f12bab6bdc9cd40c04605bb3ee460b6a7d0066229771ebb2eb2
+oid sha256:65f96fac9738bd743d88f80ce88e146114dc2ab55ff1e159bd8b01a0222db339
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6183574879227053,
+  "epoch": 0.927536231884058,
   "eval_steps": 4,
-  "global_step": 8,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -87,6 +87,42 @@
       "eval_samples_per_second": 247.956,
       "eval_steps_per_second": 61.989,
       "step": 8
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 32.23792266845703,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 352.3179,
+      "step": 9
+    },
+    {
+      "epoch": 0.7729468599033816,
+      "grad_norm": 32.02090072631836,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 352.533,
+      "step": 10
+    },
+    {
+      "epoch": 0.8502415458937198,
+      "grad_norm": 31.508159637451172,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 352.3194,
+      "step": 11
+    },
+    {
+      "epoch": 0.927536231884058,
+      "grad_norm": 32.63449478149414,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 352.3684,
+      "step": 12
+    },
+    {
+      "epoch": 0.927536231884058,
+      "eval_loss": 11.013041496276855,
+      "eval_runtime": 0.3545,
+      "eval_samples_per_second": 248.25,
+      "eval_steps_per_second": 62.062,
+      "step": 12
     }
   ],
   "logging_steps": 1,
@@ -106,7 +142,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 10649371410432.0,
+  "total_flos": 15974057115648.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null