Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31adc8652a5201f89142719b47cea216f9ef136185b927e9eae7f2fc492a9dd3
+oid sha256:f96eb5d5cedd40354462127d376991bcf09e7965ceafe680577e5131d247a0db
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcb5fd6a458c5b3e5d17e4ab4c6524a84f4351f2d986633b24da2ca1c867bc6c
+oid sha256:445bcb1c076bc6fa4a47c5e19425e65ab06cb23a1c9a43bc5f2cbe949dbcac33
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ade2cc482cc6277809f8b6a4e683b4df49a2f7024eeef419eecdce87b3e14d2
+oid sha256:332d05b227720963e561614b208f5e39d94130cc5b67b712d8aec704897dc6e6
 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": 0.00010947107226915287,
+  "epoch": 0.00021894214453830574,
   "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": 23.877,
       "eval_steps_per_second": 11.939,
       "step": 3
+    },
+    {
+      "epoch": 0.00014596142969220384,
+      "grad_norm": 0.9717092514038086,
+      "learning_rate": 8e-05,
+      "loss": 1.7241,
+      "step": 4
+    },
+    {
+      "epoch": 0.0001824517871152548,
+      "grad_norm": 1.0161713361740112,
+      "learning_rate": 0.0001,
+      "loss": 1.7689,
+      "step": 5
+    },
+    {
+      "epoch": 0.00021894214453830574,
+      "grad_norm": 0.9307000637054443,
+      "learning_rate": 0.00012,
+      "loss": 1.6985,
+      "step": 6
+    },
+    {
+      "epoch": 0.00021894214453830574,
+      "eval_loss": 1.840909719467163,
+      "eval_runtime": 757.7667,
+      "eval_samples_per_second": 15.228,
+      "eval_steps_per_second": 7.614,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 633654812344320.0,
+  "total_flos": 1267309624688640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null