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:b962c5ac39d90db206ec6c80332eb91065ef95d514a8275d0c8d2b5ff5bdb423
+oid sha256:ad2966bf4012d6d773783bdc5a54690f30ecf910f9cb666bdff84c63ceedcd60
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd3eb09c16c07d2eb88d1df9c99d8676075b23002721affed95f13588dbfd196
+oid sha256:501546aff4abbb8e5ed0d55f657ce42c26b8bf5f0e0260069b9a19802f21aef1
 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": 3.159699091323203e-05,
+  "epoch": 6.319398182646406e-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": 328.258,
       "eval_steps_per_second": 164.129,
       "step": 3
+    },
+    {
+      "epoch": 4.2129321217642704e-05,
+      "grad_norm": 0.023038163781166077,
+      "learning_rate": 8e-05,
+      "loss": 10.3759,
+      "step": 4
+    },
+    {
+      "epoch": 5.2661651522053385e-05,
+      "grad_norm": 0.02481148950755596,
+      "learning_rate": 0.0001,
+      "loss": 10.3778,
+      "step": 5
+    },
+    {
+      "epoch": 6.319398182646406e-05,
+      "grad_norm": 0.03077760897576809,
+      "learning_rate": 0.00012,
+      "loss": 10.3771,
+      "step": 6
+    },
+    {
+      "epoch": 6.319398182646406e-05,
+      "eval_loss": 10.377541542053223,
+      "eval_runtime": 124.0687,
+      "eval_samples_per_second": 322.225,
+      "eval_steps_per_second": 161.112,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 58189086720.0,
+  "total_flos": 109912719360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null