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:dd7319a095bc2f35e53d7cdccb4d2bef16db308bd20ebd48d2f2bfd1986651cf
+oid sha256:fee81af08f869f5a2c34eabb4c34c2abf96c685acefcbdadabb18d56e1e6970b
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:307092970386be0804186d15e121afa19be9b63ca4fbab8d4234219ee585b975
+oid sha256:4a949f718c77ec182a9ccd13d87c1cde37c514936590a08bb3e0f6258c74a4d8
 size 51244020

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:446f80a648d2f819fa63c934787dfaf3db4128562a9e44ba3a938ebc555c919e
+oid sha256:542dca4f4c2f4ea912f1b02e1fbd6839b42d4b1d7135f3519e0443bfb2f1698f
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c7e771aed15d0767bcd716ac3c7c2a79d39b0446742e8484ba6489486c5248a
+oid sha256:82753beea79d6eaa1bbe3ad074629d37591cc09b8d77714e57f18e54d7536c59
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acd737916b6271a8a6e3330cac252de23b82c5abbcc67d80b943abfa0b9b66ea
+oid sha256:283338c6301e3bea91766d4cd295197613c18b7552eb5b2cdd8eb3e1f7284015
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6746f4f13512f2063f7121f1543af0f608c42fd4c7ac6b7722370ae520eb4647
+oid sha256:f866350560f1a9ff1a0bb594631bef91082ae127cf474a6568fd389519cf8a4a
 size 15024

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": 0.00963855421686747,
+  "epoch": 0.01927710843373494,
   "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": 84.285,
       "eval_steps_per_second": 10.616,
       "step": 3
+    },
+    {
+      "epoch": 0.01285140562248996,
+      "grad_norm": 9.103033065795898,
+      "learning_rate": 8e-05,
+      "loss": 3.8705,
+      "step": 4
+    },
+    {
+      "epoch": 0.01606425702811245,
+      "grad_norm": 9.697961807250977,
+      "learning_rate": 0.0001,
+      "loss": 4.6658,
+      "step": 5
+    },
+    {
+      "epoch": 0.01927710843373494,
+      "grad_norm": 6.769638538360596,
+      "learning_rate": 0.00012,
+      "loss": 3.7274,
+      "step": 6
+    },
+    {
+      "epoch": 0.01927710843373494,
+      "eval_loss": 3.3475189208984375,
+      "eval_runtime": 6.2189,
+      "eval_samples_per_second": 84.26,
+      "eval_steps_per_second": 10.613,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2627750582026240.0,
+  "total_flos": 5064392030814208.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null