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:f6f5381cbe5ed9abfec953c5ec358c886380c619ec0c7aa644803f45f8c390a6
+oid sha256:fa16ecbefe227a68391de60ca971e794492b98da1eff24fcfe66ee500e42a8d3
 size 81576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d0ec19a69afda649778ab4d148300dc5ae59a7ede4a3c2e838b7070affed963
+oid sha256:924c78a01ad1214846bfbd44c6ad1ff6eb91749d4aa831127ee0caf101843b2c
 size 173094

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:464e6cdff3f8548ba79ace3859c72e6b06d1e045e69932eb75c584ad0e8918c8
+oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
 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": 2.8332825703539477e-05,
+  "epoch": 5.6665651407078953e-05,
   "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": 339.248,
       "eval_steps_per_second": 169.628,
       "step": 3
+    },
+    {
+      "epoch": 3.7777100938052636e-05,
+      "grad_norm": 0.15527969598770142,
+      "learning_rate": 8e-05,
+      "loss": 10.8474,
+      "step": 4
+    },
+    {
+      "epoch": 4.7221376172565795e-05,
+      "grad_norm": 0.12643839418888092,
+      "learning_rate": 0.0001,
+      "loss": 10.8279,
+      "step": 5
+    },
+    {
+      "epoch": 5.6665651407078953e-05,
+      "grad_norm": 0.1306692212820053,
+      "learning_rate": 0.00012,
+      "loss": 10.8403,
+      "step": 6
+    },
+    {
+      "epoch": 5.6665651407078953e-05,
+      "eval_loss": 10.83309268951416,
+      "eval_runtime": 131.7982,
+      "eval_samples_per_second": 338.267,
+      "eval_steps_per_second": 169.137,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 348625698816.0,
+  "total_flos": 717758791680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null