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:fcf36ebce6038f018df1ca02e3dbb2dbb4bd7d2532061abb203ff938615a76a0
+oid sha256:b11aefe9a1538f385ae21a0e6b19afb4577944491677ad225b8993d75a68501a
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15166a25491b5ac9a6c9252d27ad84d4a7fec046dccc4488b9456a52b1a60715
+oid sha256:cdfc44d11d6d5a64d35f84be1a796859fef8cb45ce4df4f9011aaf91dc79b406
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6754653e85716301771ba28f8873050ee9b84bd2ce8236f5a963bc4190620a38
+oid sha256:f207c0393f6e88e1bd3fd4a26645c2734162ee3e99b07f0d271c29cb37330a89
 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": 8.595065000179063e-05,
+  "epoch": 0.00017190130000358127,
   "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": 101.122,
       "eval_steps_per_second": 50.565,
       "step": 3
+    },
+    {
+      "epoch": 0.00011460086666905418,
+      "grad_norm": 1.3076165914535522,
+      "learning_rate": 8e-05,
+      "loss": 0.8629,
+      "step": 4
+    },
+    {
+      "epoch": 0.00014325108333631772,
+      "grad_norm": 1.1513737440109253,
+      "learning_rate": 0.0001,
+      "loss": 0.996,
+      "step": 5
+    },
+    {
+      "epoch": 0.00017190130000358127,
+      "grad_norm": 1.021554946899414,
+      "learning_rate": 0.00012,
+      "loss": 0.8655,
+      "step": 6
+    },
+    {
+      "epoch": 0.00017190130000358127,
+      "eval_loss": 0.98174649477005,
+      "eval_runtime": 143.4647,
+      "eval_samples_per_second": 102.443,
+      "eval_steps_per_second": 51.225,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 20575590285312.0,
+  "total_flos": 41151180570624.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null