Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23cde452e312748315ff7ab84d7bb0fe9bc026445498d1658ab5e3901e6c4a06
+oid sha256:dcc65a9a05b8f8e987f618b224c4a8358b7bec2c3597f1cb561b75210003824e
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:052e8b6bb9f65d7f707c04cd1bdb30cb7527b7255e26767bc19e6a796abd0762
+oid sha256:386f9089a6f13a309e5dab5131673c5ff2bbdf64b769a707ecb00302669f632b
 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": 0.010771992818671455,
+  "epoch": 0.02154398563734291,
   "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": 23.234,
       "eval_steps_per_second": 11.617,
       "step": 3
+    },
+    {
+      "epoch": 0.01436265709156194,
+      "grad_norm": 3.353957176208496,
+      "learning_rate": 8e-05,
+      "loss": 3.8607,
+      "step": 4
+    },
+    {
+      "epoch": 0.017953321364452424,
+      "grad_norm": 3.642730951309204,
+      "learning_rate": 0.0001,
+      "loss": 3.4281,
+      "step": 5
+    },
+    {
+      "epoch": 0.02154398563734291,
+      "grad_norm": 4.439634799957275,
+      "learning_rate": 0.00012,
+      "loss": 2.9842,
+      "step": 6
+    },
+    {
+      "epoch": 0.02154398563734291,
+      "eval_loss": 2.8470635414123535,
+      "eval_runtime": 5.7073,
+      "eval_samples_per_second": 20.675,
+      "eval_steps_per_second": 10.338,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -55,7 +84,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 494346877009920.0,
+  "total_flos": 988693754019840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null