Training in progress, step 10, checkpoint

last-checkpoint/adapter_config.json

@@ -21,11 +21,11 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "gate_proj",
-    "v_proj",
-    "q_proj",
     "down_proj",
+    "q_proj",
+    "v_proj",
     "up_proj",
+    "gate_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3a01ceb740d08102122da6b511b028ee8d2396427d53cb5e1cacc81f061dc60
+oid sha256:d25b9714157c1a8a59d03e7811037a73130985bf9428ab5d558677e5415250f0
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03786f759a729f1f35a952d3a54a045233d458322c46721ecdafd30eff8b0e14
+oid sha256:28ceed3b0b3921387ac1e0da6366406a9efdf2dbf77ec4323e6384622a156390
 size 160172858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:200897803867d9476163ce84baa477ea4bfc2d20fbca1d606afa2d969206fa8c
+oid sha256:a3efe221c4a0adf497082884c488f9d91c42d1d873e72d47409fbf104eb83048
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00012564260959700132,
+  "epoch": 0.0001396028995522237,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,9 +18,9 @@
     {
       "epoch": 1.396028995522237e-05,
       "eval_loss": 1.870382308959961,
-      "eval_runtime": 1878.2928,
-      "eval_samples_per_second": 8.029,
-      "eval_steps_per_second": 8.029,
+      "eval_runtime": 1842.0549,
+      "eval_samples_per_second": 8.187,
+      "eval_steps_per_second": 8.187,
       "step": 1
     },
     {
@@ -40,14 +40,14 @@
     {
       "epoch": 4.188086986566711e-05,
       "eval_loss": 1.870382308959961,
-      "eval_runtime": 1814.1651,
-      "eval_samples_per_second": 8.313,
-      "eval_steps_per_second": 8.313,
+      "eval_runtime": 1823.007,
+      "eval_samples_per_second": 8.273,
+      "eval_steps_per_second": 8.273,
       "step": 3
     },
     {
       "epoch": 5.584115982088948e-05,
-      "grad_norm": 0.47626373171806335,
+      "grad_norm": 0.45489802956581116,
       "learning_rate": 2e-05,
       "loss": 1.6525,
       "step": 4
@@ -61,17 +61,17 @@
     },
     {
       "epoch": 8.376173973133422e-05,
-      "grad_norm": 0.632369339466095,
+      "grad_norm": 0.6043833494186401,
       "learning_rate": 4e-05,
       "loss": 1.5735,
       "step": 6
     },
     {
       "epoch": 8.376173973133422e-05,
-      "eval_loss": 1.8685113191604614,
-      "eval_runtime": 1813.0543,
-      "eval_samples_per_second": 8.318,
-      "eval_steps_per_second": 8.318,
+      "eval_loss": 1.8686633110046387,
+      "eval_runtime": 1822.7895,
+      "eval_samples_per_second": 8.274,
+      "eval_steps_per_second": 8.274,
       "step": 6
     },
     {
@@ -83,25 +83,32 @@
     },
     {
       "epoch": 0.00011168231964177897,
-      "grad_norm": 0.616361141204834,
+      "grad_norm": 0.5930614471435547,
       "learning_rate": 6e-05,
-      "loss": 1.8794,
+      "loss": 1.8795,
       "step": 8
     },
     {
       "epoch": 0.00012564260959700132,
       "grad_norm": NaN,
       "learning_rate": 6e-05,
-      "loss": 1.6309,
+      "loss": 1.6314,
       "step": 9
     },
     {
       "epoch": 0.00012564260959700132,
-      "eval_loss": 1.8624062538146973,
-      "eval_runtime": 1806.2004,
-      "eval_samples_per_second": 8.35,
-      "eval_steps_per_second": 8.35,
+      "eval_loss": 1.862870216369629,
+      "eval_runtime": 1821.1166,
+      "eval_samples_per_second": 8.281,
+      "eval_steps_per_second": 8.281,
       "step": 9
+    },
+    {
+      "epoch": 0.0001396028995522237,
+      "grad_norm": 0.5115928649902344,
+      "learning_rate": 8e-05,
+      "loss": 1.7711,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1465859822321664.0,
+  "total_flos": 1628733135912960.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8592505319a0e1bd652dbec69d0ae190ac2673d977246a6c07d54713cd9bce43
+oid sha256:41e2120fce261a3f11caf9498f0f2c7c47b2d4840984af1e8cfb44d3982cfeb2
 size 6776