Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c294cd0c6b1d9931d82f9968ace9f7c4197cb2c0a829ff534100e2895d764865
+oid sha256:a3e9efbd3b35a880473c3986d1f0610545a9e58181dcac19fedfcdb8564b1749
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a3ee1ac1962dbd37d23d582879e628ec279374bd7afa471dfead4657fb764cb
+oid sha256:5570667e51bed5606dec9c652265758106b916b1bbadbe19317a98a8ca27da84
 size 335922386

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c29f02e164311fe4a45db08438e2bfba5f396129651e19414b291d356298d13
+oid sha256:b9657b853d16ad117cbb02515201a54c98db40e05b3c6fb54a2206b8358319a6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:597f39656b6d73311596ad567711a9a97d32a442a44c7d7bbe0976f3566ac082
+oid sha256:b7d7ac289bc1b743194258411c198358709e8025e51ba5892e5f4d51998e7e98
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6e60585a48d6a308f2186d4152318b635e41f981ffb48725379e85eb2b6d23e
+oid sha256:700fb7a907adbb73a86234d060e7eae1445b17cde074f56072436473fca651bf
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe8843036bdd815161bc9d548449bb599803263a838f45c34e9a3bbcd5efaefe
+oid sha256:9821890e8af12d14f4012cbbf7bc9c083017f56cfd57cc305c2c4bbf19c5b276
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15071590052750566,
+  "epoch": 0.30143180105501133,
   "eval_steps": 500,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -182,6 +182,181 @@
       "learning_rate": 0.00010654031292301432,
       "loss": 0.1585,
       "step": 25
+    },
+    {
+      "epoch": 0.15674453654860587,
+      "grad_norm": 0.2357844114303589,
+      "learning_rate": 0.0001,
+      "loss": 0.1181,
+      "step": 26
+    },
+    {
+      "epoch": 0.1627731725697061,
+      "grad_norm": 0.32542815804481506,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.2239,
+      "step": 27
+    },
+    {
+      "epoch": 0.16880180859080632,
+      "grad_norm": 0.27462485432624817,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.1411,
+      "step": 28
+    },
+    {
+      "epoch": 0.17483044461190655,
+      "grad_norm": 0.3306806683540344,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.1945,
+      "step": 29
+    },
+    {
+      "epoch": 0.1808590806330068,
+      "grad_norm": 0.20712682604789734,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.108,
+      "step": 30
+    },
+    {
+      "epoch": 0.186887716654107,
+      "grad_norm": 0.25769761204719543,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.1467,
+      "step": 31
+    },
+    {
+      "epoch": 0.19291635267520724,
+      "grad_norm": 0.22794191539287567,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.1393,
+      "step": 32
+    },
+    {
+      "epoch": 0.19894498869630747,
+      "grad_norm": 0.22670631110668182,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.1157,
+      "step": 33
+    },
+    {
+      "epoch": 0.20497362471740768,
+      "grad_norm": 0.21888034045696259,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.1228,
+      "step": 34
+    },
+    {
+      "epoch": 0.21100226073850792,
+      "grad_norm": 0.21215690672397614,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.1263,
+      "step": 35
+    },
+    {
+      "epoch": 0.21703089675960813,
+      "grad_norm": 0.2192404419183731,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.133,
+      "step": 36
+    },
+    {
+      "epoch": 0.22305953278070836,
+      "grad_norm": 0.25261539220809937,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.1651,
+      "step": 37
+    },
+    {
+      "epoch": 0.2290881688018086,
+      "grad_norm": 0.2244417369365692,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.1253,
+      "step": 38
+    },
+    {
+      "epoch": 0.2351168048229088,
+      "grad_norm": 0.22674843668937683,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.1354,
+      "step": 39
+    },
+    {
+      "epoch": 0.24114544084400905,
+      "grad_norm": 0.1793588250875473,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.0989,
+      "step": 40
+    },
+    {
+      "epoch": 0.24717407686510928,
+      "grad_norm": 0.20526793599128723,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.1263,
+      "step": 41
+    },
+    {
+      "epoch": 0.2532027128862095,
+      "grad_norm": 0.2529662847518921,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.1717,
+      "step": 42
+    },
+    {
+      "epoch": 0.2592313489073097,
+      "grad_norm": 0.2361597716808319,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.1353,
+      "step": 43
+    },
+    {
+      "epoch": 0.26525998492840996,
+      "grad_norm": 0.25286707282066345,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.1714,
+      "step": 44
+    },
+    {
+      "epoch": 0.2712886209495102,
+      "grad_norm": 0.1881972849369049,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.0928,
+      "step": 45
+    },
+    {
+      "epoch": 0.2773172569706104,
+      "grad_norm": 0.16801650822162628,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.0906,
+      "step": 46
+    },
+    {
+      "epoch": 0.28334589299171065,
+      "grad_norm": 0.2937343120574951,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.2129,
+      "step": 47
+    },
+    {
+      "epoch": 0.28937452901281085,
+      "grad_norm": 0.18096446990966797,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.1005,
+      "step": 48
+    },
+    {
+      "epoch": 0.29540316503391106,
+      "grad_norm": 0.2875116467475891,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.1927,
+      "step": 49
+    },
+    {
+      "epoch": 0.30143180105501133,
+      "grad_norm": 0.21270711719989777,
+      "learning_rate": 0.0,
+      "loss": 0.136,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -196,12 +371,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.8695559867845837e+17,
+  "total_flos": 3.6797609962530406e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null