Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1a4e9bf200f31ecb554db776a794400f92da2d2070d6ee22ed2afcc8491107b
+oid sha256:e7afee5b77c973a47a8e24a0dacbef308c512bfc5dc8975af7b9672f75571233
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc181caa174e2d50039ffda60bac31a46a77ec6cbddea869afe9255a9f561025
+oid sha256:e7fc17d267c2d1260cf74c7f48be0b25e1fcb556c094b2116a3d6c7183396855
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24452859dba72846bbbf77a83a06c5e00d23e619757769430d8bc11e3d2bfef8
+oid sha256:192f0b407dbacf0c2b575154416f6b58ccc968389aba4b372a0f03a786ad6139
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0032094142818935543,
+  "epoch": 0.006418828563787109,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 7.026,
       "eval_steps_per_second": 3.513,
       "step": 3
+    },
+    {
+      "epoch": 0.004279219042524739,
+      "grad_norm": 11.762137413024902,
+      "learning_rate": 8e-05,
+      "loss": 14.5246,
+      "step": 4
+    },
+    {
+      "epoch": 0.005349023803155924,
+      "grad_norm": 15.911622047424316,
+      "learning_rate": 0.0001,
+      "loss": 16.0305,
+      "step": 5
+    },
+    {
+      "epoch": 0.006418828563787109,
+      "grad_norm": 19.69184112548828,
+      "learning_rate": 0.00012,
+      "loss": 14.2623,
+      "step": 6
+    },
+    {
+      "epoch": 0.006418828563787109,
+      "eval_loss": 11.754716873168945,
+      "eval_runtime": 56.5175,
+      "eval_samples_per_second": 6.971,
+      "eval_steps_per_second": 3.486,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 693586593054720.0,
+  "total_flos": 1387173186109440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null