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:a0ca59ca3c5b7af3504147e0821e4caa2038d6f68e8d3922ef6c31092afd3109
+oid sha256:afb312d6caa3d1bee581f967dd1431d04681ee66864ae5f4c64f066d18465b55
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8854bacb8f8eb41d62e0e1c9cfaa78aca889d10138b0e75950d75892c1be5c4
+oid sha256:01a6917cea3eecf51c00c302fca776210c1d6c4cef4537e392cf16c89424500b
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f539dc9a6a8b7e3c2df4050a60d03c6feb3292b4a9f73e4e9fc1949690e3447
+oid sha256:75b7fe1ed9d1a988cf26f4ac07eea6ab570c3b37f92d1c4968cd69d6c61bd803
 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": 0.011131725417439703,
+  "epoch": 0.022263450834879406,
   "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": 4.277,
       "eval_steps_per_second": 2.139,
       "step": 3
+    },
+    {
+      "epoch": 0.014842300556586271,
+      "grad_norm": 19.3427791595459,
+      "learning_rate": 8e-05,
+      "loss": 8.3517,
+      "step": 4
+    },
+    {
+      "epoch": 0.01855287569573284,
+      "grad_norm": 20.023731231689453,
+      "learning_rate": 0.0001,
+      "loss": 6.9941,
+      "step": 5
+    },
+    {
+      "epoch": 0.022263450834879406,
+      "grad_norm": 19.472457885742188,
+      "learning_rate": 0.00012,
+      "loss": 5.532,
+      "step": 6
+    },
+    {
+      "epoch": 0.022263450834879406,
+      "eval_loss": 3.4154958724975586,
+      "eval_runtime": 26.993,
+      "eval_samples_per_second": 4.223,
+      "eval_steps_per_second": 2.112,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4451323701362688.0,
+  "total_flos": 8902647402725376.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null