Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8db51255889bd61f635be352dff3d9e4a0abc744b0b1d64b1f23719a89dcebdb
+oid sha256:38473b4e544d716c7710f10d2a256a510772706e172d34efc6c6023faed8d194
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1a3ee09e1b649c4c945bb2fa2c72d90f8a9954ddfdb6c78b82b8debe500707e
+oid sha256:afacdece9ebc131573c6dba1592c448a00862db876f6d4c7fbe65ec9bacdfeed
 size 97487290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91b24fc1ce0ebd43a5a2c02d4cd0e240082f722605ae31afde9e2954adcd4790
+oid sha256:c6cd39cdb37120f55361cd5e0069f61be89d255f23a8450b4d3163474d73427f
 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": 0.0005638037962788949,
+  "epoch": 0.0011276075925577898,
   "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": 20.926,
       "eval_steps_per_second": 20.926,
       "step": 3
+    },
+    {
+      "epoch": 0.0007517383950385266,
+      "grad_norm": 0.3058125972747803,
+      "learning_rate": 8e-05,
+      "loss": 2.1183,
+      "step": 4
+    },
+    {
+      "epoch": 0.0009396729937981583,
+      "grad_norm": 0.44318097829818726,
+      "learning_rate": 0.0001,
+      "loss": 2.2092,
+      "step": 5
+    },
+    {
+      "epoch": 0.0011276075925577898,
+      "grad_norm": 0.3183535933494568,
+      "learning_rate": 0.00012,
+      "loss": 2.2227,
+      "step": 6
+    },
+    {
+      "epoch": 0.0011276075925577898,
+      "eval_loss": 2.2024617195129395,
+      "eval_runtime": 54.1467,
+      "eval_samples_per_second": 20.703,
+      "eval_steps_per_second": 20.703,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 208716913704960.0,
+  "total_flos": 417433827409920.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null