Training in progress, step 378, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edce236ed9d28437ecbd25f57fa405e7811548ad06d25e7ee2e03e35cae474e7
+oid sha256:b094796a3043040fc20becd553325e34a769103a7c5d10ae18b6158c1c1849f5
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecbd8daf8d8f6dadeaaf1894e705edcf7b4cb93a2fe07927e49405c98edc3627
+oid sha256:39557afe36d5e189e1e04d3e99f8bd45f3b28f96a8c1d63dc4f40cb53e95a33c
 size 197158

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:585086fc4d882c3b00033d27af061feb3e3aba0472ded903abd7a66ec1908052
+oid sha256:119fe715ac3c860103e8a9debc4f03af2063cfd89cb1715847cde9fb4c7fc469
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06715ba1620389ca0b4addc4d3a5d2e99d004e57928b3fd13d4028448769c87c
+oid sha256:5c871a29aafc4cc2e188c2a1192be10629a3367edb40bd6f57fc891f110c0b32
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:968865e3b0ca4449ed9a6d127f5f982867a1e9d962247cd559315d44137c3980
+oid sha256:5505f1fb01d87dde14fc81379497ded1f5f974f64cedaf83d975d1311d82a953
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4861407560531aa131144dfce65910431552a00481de242fe5bff99a269dba47
+oid sha256:eea6038eeb267887dcd89f798edd4e04b2ce9df9d4541d4f61f2a0a5c24c73a3
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10affc9ced28dcfaf0d40e3497a97c8e7416bd057324538f99a7e1756fd84408
+oid sha256:6ac207b57c6cefba3838e335ba7ebf320ffdaee8162f1c0afc72ea9ad9f0725f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8778576094056172,
+  "epoch": 0.9875898105813194,
   "eval_steps": 42,
-  "global_step": 336,
+  "global_step": 378,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -863,6 +863,112 @@
       "eval_samples_per_second": 775.492,
       "eval_steps_per_second": 24.366,
       "step": 336
+    },
+    {
+      "epoch": 0.8856956237753103,
+      "grad_norm": 0.01870771311223507,
+      "learning_rate": 2.43550361297047e-05,
+      "loss": 11.9178,
+      "step": 339
+    },
+    {
+      "epoch": 0.8935336381450033,
+      "grad_norm": 0.014654111117124557,
+      "learning_rate": 2.353425010381063e-05,
+      "loss": 11.9177,
+      "step": 342
+    },
+    {
+      "epoch": 0.9013716525146963,
+      "grad_norm": 0.01838817447423935,
+      "learning_rate": 2.272325493947257e-05,
+      "loss": 11.9171,
+      "step": 345
+    },
+    {
+      "epoch": 0.9092096668843893,
+      "grad_norm": 0.021683456376194954,
+      "learning_rate": 2.192235065998126e-05,
+      "loss": 11.9179,
+      "step": 348
+    },
+    {
+      "epoch": 0.9170476812540823,
+      "grad_norm": 0.02190260961651802,
+      "learning_rate": 2.1131833555559037e-05,
+      "loss": 11.917,
+      "step": 351
+    },
+    {
+      "epoch": 0.9248856956237753,
+      "grad_norm": 0.014892240054905415,
+      "learning_rate": 2.0351996073748713e-05,
+      "loss": 11.917,
+      "step": 354
+    },
+    {
+      "epoch": 0.9327237099934683,
+      "grad_norm": 0.020150186493992805,
+      "learning_rate": 1.9583126711224343e-05,
+      "loss": 11.9175,
+      "step": 357
+    },
+    {
+      "epoch": 0.9405617243631613,
+      "grad_norm": 0.01918022148311138,
+      "learning_rate": 1.8825509907063327e-05,
+      "loss": 11.9172,
+      "step": 360
+    },
+    {
+      "epoch": 0.9483997387328543,
+      "grad_norm": 0.020093288272619247,
+      "learning_rate": 1.807942593751973e-05,
+      "loss": 11.9177,
+      "step": 363
+    },
+    {
+      "epoch": 0.9562377531025473,
+      "grad_norm": 0.015267434529960155,
+      "learning_rate": 1.7345150812337564e-05,
+      "loss": 11.9167,
+      "step": 366
+    },
+    {
+      "epoch": 0.9640757674722403,
+      "grad_norm": 0.01452693808823824,
+      "learning_rate": 1.66229561726426e-05,
+      "loss": 11.9178,
+      "step": 369
+    },
+    {
+      "epoch": 0.9719137818419333,
+      "grad_norm": 0.01645076647400856,
+      "learning_rate": 1.5913109190450032e-05,
+      "loss": 11.9171,
+      "step": 372
+    },
+    {
+      "epoch": 0.9797517962116263,
+      "grad_norm": 0.02012869343161583,
+      "learning_rate": 1.5215872469825682e-05,
+      "loss": 11.9169,
+      "step": 375
+    },
+    {
+      "epoch": 0.9875898105813194,
+      "grad_norm": 0.015907544642686844,
+      "learning_rate": 1.4531503949737108e-05,
+      "loss": 11.9176,
+      "step": 378
+    },
+    {
+      "epoch": 0.9875898105813194,
+      "eval_loss": 11.916740417480469,
+      "eval_runtime": 3.3252,
+      "eval_samples_per_second": 775.289,
+      "eval_steps_per_second": 24.359,
+      "step": 378
     }
   ],
   "logging_steps": 3,
@@ -882,7 +988,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6481603461120.0,
+  "total_flos": 7292707799040.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null