Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b43063bcba76430f0d8ec4a5b0673974e818fe719b90d1ebb17f28e980c0c36
+oid sha256:bee0f8a2b901490c86eef040f84de4ae7fb631697217e62d2bdd7372db403bb5
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9735f2513bb40fd6f1cd1587ee911b05b3cb2b44eaa268f0f457d756ec83f53
+oid sha256:7de9e10d042c98a1ba2d679f3a262f6fa5821a17d684072b5fb4191f334cbe60
 size 49846260

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74bdc9d2469487aaea76dad4b5d1315319095997cc1dc44c825c933091c205d7
+oid sha256:0634cfd3a595bdc9deaef4fa576cb8d5ef5b9c967ab34b22dc88c56b5fe30283
 size 15920

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c89ad4c7f892e8e164147c1350c53cb6af3244cb965f2a6253c536bcf59fdb3
+oid sha256:9f871dcddb3a16517740514744491a9fbb42a57ff950fa5584abe57e7f9bec7a
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:478b671c87bf0b74dd77de05f7d104729acdd8923e92060c187075c178a27520
+oid sha256:d0a54cd94578a84a985c5e49180616033169de995db4e81779ab471b641aae11
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcf10ab3b250e324d50f574c4d281205a1e897b9e3a614304eb3f0fd07d07a1a
+oid sha256:e8ee91319a9a983a75121cb19712b95b91e7b2b1f75e8835fc9e7d00fe28cbc2
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdeeb979014719bfd4ca0db2adb603581d46ba5b7a013036375324966ea5239d
+oid sha256:127f0207df027db84a408f13e3d9013cb7bab300a40c0f44e66959df53905984
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:637629469afc00b793771622fd4597cbeaac8535856bdf134fe1a76ba8ea1a58
+oid sha256:d1ef139c25fc2e488bff40dd5eeea268125cefd1f9f75ff908cdfea5cf13d729
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2291200f3073bac5aad4725021610d0eb002dc21d45de12f1336cffca37ff02b
+oid sha256:36f262e0350c5145a3741ec496e88c275b236cc6b18ad5b962dc0f0cc997870c
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e86568a3aea0196e9198e30c2b80e8557dbcc458f7c3f35a612a52e25891a0ef
+oid sha256:0e689191ffaaead2363233c20f7c2f8ba604a3aaa2ea1af4f9a817f6e3496763
 size 15984

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": 0.0547945205479452,
+  "epoch": 0.1095890410958904,
   "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": 49.719,
       "eval_steps_per_second": 6.415,
       "step": 3
+    },
+    {
+      "epoch": 0.0730593607305936,
+      "grad_norm": 0.4484165608882904,
+      "learning_rate": 8e-05,
+      "loss": 1.0483,
+      "step": 4
+    },
+    {
+      "epoch": 0.091324200913242,
+      "grad_norm": 0.4434252083301544,
+      "learning_rate": 0.0001,
+      "loss": 1.0122,
+      "step": 5
+    },
+    {
+      "epoch": 0.1095890410958904,
+      "grad_norm": 0.4385027587413788,
+      "learning_rate": 0.00012,
+      "loss": 0.9783,
+      "step": 6
+    },
+    {
+      "epoch": 0.1095890410958904,
+      "eval_loss": 0.9256500601768494,
+      "eval_runtime": 1.8637,
+      "eval_samples_per_second": 49.9,
+      "eval_steps_per_second": 6.439,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6707623030161408.0,
+  "total_flos": 1.3415246060322816e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null