Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b859613e399297d4bf61cd4411e55fcfac72f860c013731303d3762e13ac31f
+oid sha256:3b459285a37d04c8f160cdc8470529f29412122305875d0a5cdfceec1d52fa10
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01aa4f72d00bd6c18f11d13b97a7ffa5309f6b7e77fa46d8fe6488ca5b4e2959
+oid sha256:6466a91056a57468ff5821ab9ce8250281c9192543c742716d80466dcd2e315c
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a75ae50ef05b0af49c3969f35c925149f1546408e414606cff98807664e1d74
+oid sha256:6a05e8c8d4f4ea5c6947dad0aa69b6f43b41a930416dd2c1ca05214316cbbf69
 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": 0.0017052721330112265,
+  "epoch": 0.003410544266022453,
   "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": 66.722,
       "eval_steps_per_second": 33.406,
       "step": 3
+    },
+    {
+      "epoch": 0.002273696177348302,
+      "grad_norm": 5.7656731605529785,
+      "learning_rate": 8e-05,
+      "loss": 11.6239,
+      "step": 4
+    },
+    {
+      "epoch": 0.002842120221685377,
+      "grad_norm": 5.779434680938721,
+      "learning_rate": 0.0001,
+      "loss": 8.2429,
+      "step": 5
+    },
+    {
+      "epoch": 0.003410544266022453,
+      "grad_norm": 4.3664422035217285,
+      "learning_rate": 0.00012,
+      "loss": 10.265,
+      "step": 6
+    },
+    {
+      "epoch": 0.003410544266022453,
+      "eval_loss": 2.0713918209075928,
+      "eval_runtime": 11.1833,
+      "eval_samples_per_second": 66.26,
+      "eval_steps_per_second": 33.175,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 26274378547200.0,
+  "total_flos": 50672015769600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null