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:e937a81cc3c05512f0c4f6fd10802105112288e2fdaea5e80bad7e379a0893f5
+oid sha256:45c1fa3a1370bc139a59874712a8743eabc6a023bbde5a943f6143b9c9047cfe
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c861d19e304e30cb0584badd34454cd672e564e0d2d7d3a70b1ad557c879788
+oid sha256:8e9c5d5039ac7295aabe22ca9ff942f5698123d7432c83e94d1e6071b2c5303c
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d63550aef934dca682dbe4a2a94ff2b1a5fd333f064103ac7badea775ed97a9
+oid sha256:3640687a5ab54e1feaf9fadb6873fdcdbca5f107b040d8f53bce84f5dfd97d33
 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": 0.0010686615014694097,
+  "epoch": 0.0021373230029388193,
   "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": 35.513,
       "eval_steps_per_second": 17.757,
       "step": 3
+    },
+    {
+      "epoch": 0.0014248820019592127,
+      "grad_norm": 1.4197344779968262,
+      "learning_rate": 8e-05,
+      "loss": 1.5582,
+      "step": 4
+    },
+    {
+      "epoch": 0.0017811025024490159,
+      "grad_norm": 0.8563295006752014,
+      "learning_rate": 0.0001,
+      "loss": 0.9642,
+      "step": 5
+    },
+    {
+      "epoch": 0.0021373230029388193,
+      "grad_norm": 0.9468586444854736,
+      "learning_rate": 0.00012,
+      "loss": 1.2557,
+      "step": 6
+    },
+    {
+      "epoch": 0.0021373230029388193,
+      "eval_loss": 2.194425582885742,
+      "eval_runtime": 33.2939,
+      "eval_samples_per_second": 35.502,
+      "eval_steps_per_second": 17.751,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 162531632480256.0,
+  "total_flos": 337565698228224.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null