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:adbfee28f6a717d1334bd0edc70154ff0d334cd85d3c0d400d8e74584249ef43
+oid sha256:d1f090196374399294138eba115b1d49cb39b64055da666dca60eeb76869ef3e
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dedc21dc2cd907285bd257a52594b6c42fed68cbc62cb73fed38ee429f244b8e
+oid sha256:71ef0ac4047cf918a26ef6bb15fb7a52f3223d00cba2a4a9275953afc3aea46a
 size 63974

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": 0.00022596742302984652,
+  "epoch": 0.00045193484605969304,
   "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": 399.392,
       "eval_steps_per_second": 199.696,
       "step": 3
+    },
+    {
+      "epoch": 0.0003012898973731287,
+      "grad_norm": 0.07609041035175323,
+      "learning_rate": 8e-05,
+      "loss": 10.3737,
+      "step": 4
+    },
+    {
+      "epoch": 0.00037661237171641087,
+      "grad_norm": 0.07180183380842209,
+      "learning_rate": 0.0001,
+      "loss": 10.3677,
+      "step": 5
+    },
+    {
+      "epoch": 0.00045193484605969304,
+      "grad_norm": 0.0721636489033699,
+      "learning_rate": 0.00012,
+      "loss": 10.3721,
+      "step": 6
+    },
+    {
+      "epoch": 0.00045193484605969304,
+      "eval_loss": 10.366961479187012,
+      "eval_runtime": 14.5198,
+      "eval_samples_per_second": 384.992,
+      "eval_steps_per_second": 192.496,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 38792724480.0,
+  "total_flos": 77585448960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null