Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -16,16 +16,16 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "o_proj",
     "gate_proj",
-    "down_proj",
+    "up_proj",
     "v_proj",
     "k_proj",
+    "down_proj",
+    "o_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46824cbb33d41feb984b47d79ab48617a092bf6e4876342b666ffd09f1f7809f
-size 83945296
+oid sha256:7e6b719b5eeeb56d4de0a644f729b7448af65bee5d335a18bf3ea2545876a60b
+size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74e30d3405912663d6f63031e1c218aeb74d9f4e3f44a815cf07c817af377a38
-size 43122580
+oid sha256:2899f8c5e05ce7c26dbe13e32826440b6bbe7bb5d1cafb2d46ff3c23c8de0534
+size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be12eb81f8b5abab0215725b5211cac3fee2a892944bd06332e4465ced24e47b
+oid sha256:1a8ac7cc701a352c55a6691931bbc8b9427ade77b79e8b9c5d081e5ab4bb0935
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:16daf775c694a5f3796de8e8b2292f8210c83caa8beac1bdff3a005d9cc2ad43
 size 1064

last-checkpoint/trainer_state.json

@@ -1,106 +1,41 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004253056884635832,
+  "epoch": 0.005103668261562998,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0004253056884635832,
-      "grad_norm": 0.4657903015613556,
-      "learning_rate": 1e-05,
-      "loss": 1.4391,
+      "epoch": 0.0017012227538543328,
+      "grad_norm": 0.2675527036190033,
+      "learning_rate": 0.0001,
+      "loss": 1.514,
       "step": 1
     },
     {
-      "epoch": 0.0004253056884635832,
+      "epoch": 0.0017012227538543328,
       "eval_loss": 1.5264209508895874,
-      "eval_runtime": 401.2029,
-      "eval_samples_per_second": 2.468,
-      "eval_steps_per_second": 2.468,
+      "eval_runtime": 382.3151,
+      "eval_samples_per_second": 2.589,
+      "eval_steps_per_second": 2.589,
       "step": 1
     },
     {
-      "epoch": 0.0008506113769271664,
-      "grad_norm": 0.4855019450187683,
-      "learning_rate": 2e-05,
-      "loss": 1.5823,
+      "epoch": 0.0034024455077086655,
+      "grad_norm": 0.26320022344589233,
+      "learning_rate": 0.0002,
+      "loss": 1.5098,
       "step": 2
     },
     {
-      "epoch": 0.0012759170653907496,
-      "grad_norm": 0.5047929883003235,
-      "learning_rate": 3e-05,
-      "loss": 1.5517,
+      "epoch": 0.005103668261562998,
+      "grad_norm": 0.3753179609775543,
+      "learning_rate": 0.0003,
+      "loss": 1.5717,
       "step": 3
-    },
-    {
-      "epoch": 0.0017012227538543328,
-      "grad_norm": 0.46675997972488403,
-      "learning_rate": 4e-05,
-      "loss": 1.4802,
-      "step": 4
-    },
-    {
-      "epoch": 0.002126528442317916,
-      "grad_norm": 0.5267013907432556,
-      "learning_rate": 5e-05,
-      "loss": 1.6853,
-      "step": 5
-    },
-    {
-      "epoch": 0.002126528442317916,
-      "eval_loss": 1.5186384916305542,
-      "eval_runtime": 393.879,
-      "eval_samples_per_second": 2.513,
-      "eval_steps_per_second": 2.513,
-      "step": 5
-    },
-    {
-      "epoch": 0.002551834130781499,
-      "grad_norm": 0.5022115707397461,
-      "learning_rate": 6e-05,
-      "loss": 1.4265,
-      "step": 6
-    },
-    {
-      "epoch": 0.0029771398192450825,
-      "grad_norm": 0.643319845199585,
-      "learning_rate": 7e-05,
-      "loss": 1.4905,
-      "step": 7
-    },
-    {
-      "epoch": 0.0034024455077086655,
-      "grad_norm": 0.6432769894599915,
-      "learning_rate": 8e-05,
-      "loss": 1.3826,
-      "step": 8
-    },
-    {
-      "epoch": 0.003827751196172249,
-      "grad_norm": 0.7721529006958008,
-      "learning_rate": 9e-05,
-      "loss": 1.3709,
-      "step": 9
-    },
-    {
-      "epoch": 0.004253056884635832,
-      "grad_norm": 0.8031099438667297,
-      "learning_rate": 0.0001,
-      "loss": 1.6038,
-      "step": 10
-    },
-    {
-      "epoch": 0.004253056884635832,
-      "eval_loss": 1.4016755819320679,
-      "eval_runtime": 381.7384,
-      "eval_samples_per_second": 2.593,
-      "eval_steps_per_second": 2.593,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -115,12 +50,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 3699128496291840.0,
+  "total_flos": 4451323701362688.0,
   "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:b1b26d77f07d40b41244e2cca0d22519aa753bf94bfc954e13e9bd1805613419
+oid sha256:db7e52d6b77b78161a016f25ec3622ecd2cb128a7397d9cbf5cea2fec2c01544
 size 6776