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:c5049c9aa84e3bc6545d6713811b98126d215c898b0cd5716d9ba8505da43c99
+oid sha256:77c0b5e03009e69da3333a70afa23c7b5b0a993a7a7bb639fab5833014a3edc4
 size 124756544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ce88f07172b2b36d592461714bd588e6786c7727b6d7747bc93d90e6193ba0c
+oid sha256:c69f7b4e958e391469cbac9ba5c7aeb1448a2286545ea79561e2b86e2c696dec
 size 63958740

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1232a2d0c89b7975e4959e6ccb632925c42cdfc7084ec4d7506dd39bc50b39b
+oid sha256:6dee4d5b27e291e54604657b0419725531a46b79101c42b4fcc524425de489f6
 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": 0.002188183807439825,
+  "epoch": 0.00437636761487965,
   "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": 20.771,
       "eval_steps_per_second": 10.386,
       "step": 3
+    },
+    {
+      "epoch": 0.0029175784099197666,
+      "grad_norm": 1.6993635892868042,
+      "learning_rate": 8e-05,
+      "loss": 2.3704,
+      "step": 4
+    },
+    {
+      "epoch": 0.0036469730123997084,
+      "grad_norm": 1.0507618188858032,
+      "learning_rate": 0.0001,
+      "loss": 2.1938,
+      "step": 5
+    },
+    {
+      "epoch": 0.00437636761487965,
+      "grad_norm": 1.165635347366333,
+      "learning_rate": 0.00012,
+      "loss": 1.9088,
+      "step": 6
+    },
+    {
+      "epoch": 0.00437636761487965,
+      "eval_loss": 2.006481647491455,
+      "eval_runtime": 27.9404,
+      "eval_samples_per_second": 20.687,
+      "eval_steps_per_second": 10.343,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 989421927137280.0,
+  "total_flos": 1978843854274560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null