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:a1e7ef161c12f89cbb3b0f934bd0813db0bfa3524f697e07db353bd0006171e8
+oid sha256:a043732993f7c31cdf66025809eb944de5cad7cf74801b421b832fabf636bafa
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abf388a1f499e0704d25264034e8859f57b83c475fa3df0ca343cdcaffebc7d8
+oid sha256:066a500f14185f1c89daade1a45efdecf932058931c37bebcdbe6044807a69b0
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b173ac9ab56406e53f02ac343bf22d13dc84cb35b451121151594928dcc2f4cd
+oid sha256:09acce823b858db1a079a05549bd8528f2fec468928dba778f7e8bdddcd10eea
 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": 0.00020496353357131876,
+  "epoch": 0.0004099270671426375,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -36,6 +36,35 @@
       "eval_samples_per_second": 20.939,
       "eval_steps_per_second": 10.471,
       "step": 3
+    },
+    {
+      "epoch": 0.000273284711428425,
+      "grad_norm": 3.1876351833343506,
+      "learning_rate": 8e-05,
+      "loss": 4.5918,
+      "step": 4
+    },
+    {
+      "epoch": 0.00034160588928553126,
+      "grad_norm": 3.4983630180358887,
+      "learning_rate": 0.0001,
+      "loss": 4.8883,
+      "step": 5
+    },
+    {
+      "epoch": 0.0004099270671426375,
+      "grad_norm": 3.2121989727020264,
+      "learning_rate": 0.00012,
+      "loss": 4.3112,
+      "step": 6
+    },
+    {
+      "epoch": 0.0004099270671426375,
+      "eval_loss": 4.1929216384887695,
+      "eval_runtime": 313.2443,
+      "eval_samples_per_second": 19.675,
+      "eval_steps_per_second": 9.839,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -55,7 +84,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 492949569798144.0,
+  "total_flos": 985899139596288.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null